How do I use Sally to Label an Image?

How do I use Sally, the cognitive image advisor, to label an image in my application?

Using Sally to label an image is quite simple. All you need is to make a POST request to the Sally API as given in the example below. Sally has been trained on Real Estate specific images and continues to improve its accuracy as more and more images are used for training the application. Read more about Sally here.

API Request GetLabelsForImage

POST Method:


Body: {

“imageurl”: “”,

“accesstoken”:<< your access token goes here >>


Header: Content-Type: application/json

A sample image is given below.

The API responds with the image label. In this case, the API identifies the room as a Kitchen.

API response


   “status”: {

       “code”: 200,

       “type”: “OK”,

       “message”: “Success”


   “imageAnalysis”: {

“imageName”: “kitchen_001.jpg”,

“imageInfo”: [


               “labelName”: “Kitchen”,

               “confidence”: 0.922417





Interested in trying out Sally in your application? Click here to get a trial access token.

How do I use Sally for room-by-room comparison?

A user guide for testing Sally at

Sally is a cognitive image advisory service that identifies property information from listing images. Sally automates the analysis of listing photos to:

  • Identify types of rooms – kitchen, family room, dining, game room, basement, etc
  • Identify objects in a room – brick fireplace, type of refrigerator, type of counter tops, number of sinks, etc.
  • Extract detailed property information from the photos

Sally is a neural network engine trained on terabytes of real estate imagery and it continues to learn how to perform deeper analysis. After an initial 3-month training period Sally started classifying images into different room types. After another 6-months of rigorous research, redesign, and retraining, she can now pickup objects in a room to help improve your listing data.

How do I access Sally?

You can access Sally using the URL No login credentials are required to access the trial site.

Are there any restrictions during the trial period?

During the trial period, Sally will allow you to search only for properties in the zip code 33156 in Miami, FL.

Home page

The home page of Sally is shown in the screenshot below

Enter an address to search

The Address field in the top left cornet can be used to enter an address. The possible addresses in the US are prompted as the user types the address. For the trial period, the addresses within zip code 33156 in Miami, FL can be used. You can also start with the address that is already pre-filled in the Address field.

Once the address is entered, the app requires the user to verify the address components of the Subject Property as given in the screenshot below. The filter criteria for the search can also be specified in the filter area in the top row.

Search results

The search results are shown in map view and table view as given in the screenshot below

Grid View of Search Results

The user has the option to select the Grid view of the property details section on the right side. The view is as shown in the screenshot below.

Selecting a Property for further analysis

Clicking on a pin or the property card in the right side will highlight the property on the map view along with a summary of the property details.

Select properties to compare photos

You can add up to 5 properties to compare photos with the Subject Property by clicking on the Add to Compare button next to the Address on the table view or on the thumbnail on the Grid view.

Comparing photos of selected properties

 The photos of selected properties can be compared by clicking on the Compare Photos button on the top right corner of the page. The images of the properties categorized by type, such as Exterior, Bedroom, Bathroom, Kitchen etc are displayed as in the screenshot below.

Removing a property from the compare photos view

A property can be removed by clicking on the Delete icon next to the Address of the property


Sally API Technical Details

Sally app uses two cognitive APIs – GetListingsByRadiusWithThumbnail and GetLabeledImagesByListingId

  1. GetListingsByRadiusWithThumbnail

GetListingsByRadiusWithThumbnail API returns the comparable listings within the given radius along with thumbnail images. ImageType can be passed as Input Parameter, example &ImageType=Frontage. If the input ImageType is available in the data then the API will respond with corresponding thumbnail image of that property, else the Thumbnail will be displayed on the basis of predefined priority.

API EndPoint:


  1. GetLabeledImagesByListingId

GetLabeledImagesByListingId API returns the ‘ImageUrls’ along with the ListingId, categorized on the basis of image type. For each image, corresponding image labels are also identified and displayed in the response. Up to ten ListingIDs can be provided in the same API call, separated by comma.

API EndPoint:


Sally API Documentation

Sally API documentation is available in the PropMix API documentation page under Insights APIs for GetListingsByRadiusWithThumbnail and GetLabeledImagesByListingId. in collaboration with RESO is offering 50% discount to RESO members

MANHASSET HILLS, N.Y., Oct. 17, 2017 /PRNewswire-iReach/ —, an Innovation Incubator portfolio company, announced two new capabilities to empower real estate brokers and software providers – the latest release of Sally, cognitive image advisor and an AI-driven broker insights platform called BrokerView. Sally IDX APIs will enable brokers and agents to enhance the seller/buyer experience on their IDX websites and automate and improve the quality of the content. The updated version of BrokerView, the analytics platform for Brokers from, provides a comprehensive view of the Broker’s business and the market trends along with actionable recommendations. These services are being offered in collaboration with RESO at 50% discount for RESO members

PropMix has solved the image recognition problem in real estate using our decades long real estate experience and deep AI knowledge. Sally allows IDX portal visitors to find and compare homes using the photos posted by agents. Sally has been trained on a million images to help automate the labeling of all home photos, organize them, and choose the best thumbnail image. In addition, Sally infers property details from the images and standardizes them to the Real Estate Standards Organization (RESO) data dictionary. As a result images are searchable with standard tools. This will improve SEO hits on IDX websites, and best of all customers can compare rooms side-by-side using photos.

PropMix has also released an insights and decision making platform for brokers called BrokerView. It uses big data and deep learning models to analyze real estate transactions and combines them with competitor and local and adjacent market predictions. In addition to delivering a customizable dashboard of the common metrics, BrokerView discovers the broker’s business model and generates highly targeted recommendations on neighborhoods, markets, and agents.

PropMix is collaborating with RESO to make Sally and BrokerView available to its members at a discounted price. “Image recognition enables a new breed of real estate applications with lasting impact in consumer experience, valuation, and risk management and PropMix’s Sally platform is at the forefront of that disruption” said Umesh Harigopal, CEO of PropMix. “We are looking forward to RESO members actively utilizing the platform and incorporate image recognition APIs into the RESO standards in the near future”.

The combination of image recognition, natural language processing, and big data analytics within PropMix’s Real Estate cognitive fabric is creating a comprehensive platform for AI in real estate and enabling a new generation of apps that learn and automate decision making for all participants in the real estate market.

About LLC USA LLC, an Innovation Incubator Inc portfolio company along with its subsidiary India Private Limited, offers a ground-breaking Real Estate Smart App Development Platform that enables the Real Estate ecosystem to easily consume and monetize data and insights and build Smart Apps. Strategic partners include Software Incubator and Cognub Decision Solutions the first decision science company in Real Estate. Built on industry open standards based Platform as a Service (PaaS) for global scale and bulk sync, empowers users to engage with data, make decisions using insights and build the Real estate future. Headquartered in New York, we also have presence in Boston MA, Leesburg VA, Freehold NJ in USA and Trivandrum, Kerala in India.

Media Contact: Sakeer Hassan, LLC, 7329799507,

News distributed by PR Newswire iReach:

Improve the Quality of Your Real Estate Data

PropMix published Part 1 of our latest Point of View series of articles called “Improve the Quality of Your Real Estate Data” earlier this week. The first part of the article covers in detail the relevance of data quality in Real Estate, why it is difficult to maintain good quality in Real Estate data, and ways to measure the data quality. Click here to read Part 1 of the article by Daniel Mancino, Sakeer Hassan, and Dr. Umesh Harigopal.

Recent Trends in Using Computer Vision for Real Estate

Computer Vision can be broadly defined as the processing of images so as to interpret the objects contained in them. With recent advancements in image processing, machine learning, and cognitive computing, computers are able to simulate the human visual sensory process to a large extent. The advancements in these areas in recent years have helped computer vision reach maturity levels that are several orders of magnitude advanced than what was possible even a decade ago.Computer vision is widely used in several industrial and consumer applications today. Face recognition for accessing a personal computer, tagging individuals on photos, use of robotics in manufacturing automation and quality control, analysing patient condition through remotely uploaded images, home security solutions that distinguish familiar faces from those of strangers, etc., all apply the concepts of computer vision. Autonomous, smart cars and associated technologies rely heavily on sophisticated computer vision algorithms that are still in the advanced stages of development. With the seemingly unending possibilities that computer vision offers, it is only natural that billions of dollars are invested in advancing the boundaries of this technology. The amount invested is expected to go up from USD 7 billion in 2015 to USD 50 billion by 2022, at a CAGR of 30%+ .

How is Computer Vision relevant to Real Estate?
Technology related to computer vision is making inroads into all areas of human interest, and Real Estate is no different. The recent advancements in computer vision are helping players in the industry unlock areas which have hitherto been considered impossible to achieve as a scalable solution. With the availability of significant computing power at costs that are getting reduced every quarter, the applications of computer vision is expanding at a fast pace in the industry. Some of the important applications of computer vision in Real Estate are given below.


  • Unlock listing data through photos
    According to a blog from , computer vision can help reveal hundreds of property attributes from listing photos that are typically not captured as part of the listing information. Users will now be able to understand factors that are subjective, such as the quality of natural light and vastness of the view without even stepping into the property.
  • Transform listing search to searchable images
    Users would be able to list properties using specific image characteristics, rather than what has been traditionally done using quantifiable property attributes such as beds, baths, living area etc.
  • Identify matching properties quickly
    Image based search would be able to identify properties that display similar characteristics on a whole set of attributes. Agents would be able to match properties with nuanced attribute descriptions leading to more productivity and customer satisfaction.
  • Create property details for listing just from images
    In the future, agents would be able to generate entire property details and room-wise amenities list by just uploading a set of photos. Computer vision will enable recognition of the elements contained in these images, demarcate them, and create listing information that can be uploaded directly into an MLS or a listing platform.
  • Sequence property images in a pre-defined order
    Typical MLS listings have photos of properties in a haphazard order which do not follow a sequence. Through computer vision, listing agents would be able to sort the photos quickly and efficiently in a pre-defined order before uploading to the listing platform. By adding image quality filters to this process, photos which are not good can be marked out for replacement or deletion.
  • Compare properties room-wise
    Computer vision can be used to compare multiple properties room for room in terms of space, relative location of windows and doors, natural lighting, etc. Multiple images for the same room, if available, can be grouped for better comparison and assessment. All this is possible on listings that have been entered years ago since images can be processed real-time. This can create a compelling user experience for the property buyer.


Introducing Sally, a cognitive imaging service from PropMix

Continuing on our promise during Inman Connect NYC 2017, we are now moving our image advisor service out of the labs into general availability. It has taken us over 18 TB of images and 3.2 nerd-years to train our neural network to perfection.

Sally – our Convolutional Neural Network (CNN) based deep learning platform for computer vision, has been trained specifically on residential real estate imagery and is now available as a service for anyone to leverage. Sally can look at a set of images for a home and automatically select and recommend the best picture to be your thumbnail and also reorder your photos for the best viewing experience for consumers.

Sally uses a growing library of millions of images available via PropMix to constantly train itself. Sally can now analyze each image and identify not just the type of room – kitchen, living, dining, etc. – but can also recognize what is available in the image. For instance, Sally can easily recognize the image of a kitchen along with the type of flooring, countertop, cooking amenities, shelves, sinks etc. Sally provides a score-based ranking of its recognized objects enabling the higher level algorithms to make contextual decisions for property listings, valuations, and/or fraud detection.

Expect a lot more to come from Sally in the coming months to empower sellers, buyers, agents, and appraisers in the real estate market. Please subscribe here for exciting news on Sally.

Indunia International partners with PropMix to deliver Cognitive Image Advisor – Sally

Sally will enhance user experience of listings and scale up operations of Indunia Validation Hub.

Apr 26, 2017, 9:00am ET

MANHASSET HILLS, New York, Apr 26, 2017 – Indunia International, a pioneer in adopting RESO standards in India, is piloting Sally, a cognitive imaging service powered by as part of their new beta program.

The integration will enable users of Indunia digital real estate marketplace to post listings by simply uploading images of the property and Sally will do the rest by pulling up information like property amenities, number of rooms, type of rooms etc. Sally will automatically sequence the images to achieve the best consumer experience to drive leads based on successful digital interactions derived from deep learning provided through the real estate cognitive fabric and a 22TB PropMix image library.

Indunia accepts only verified and validated listings on its marketplace and at present a major part of this is done manually using Indunia Validation Hub which is spread across India. Sally will automate a significant portion of the validation process to scale up its operations. Sally will flag postings based on a fraud score derived from historical property images and details.

“When we first discovered Sally, we immediately realized the potential it has to enhance experience of our users while posting a listing on our marketplace,” said Matt Kumar, Co-founder of Indunia International LLC and CEO of Software Incubator Inc. “While Sally enables our users to post their listings quickly with ease, the technology also helps our validation hub to verify listings before they go live. And the best part is that Sally continues to learn and improve its value impact.”

Along with providing detailed property information and insights, Indunia also provides Real 360 View of the interiors of apartments and villas of builders. Indunia Real 360 View is a realistic high quality immersive 3D visualization which is already a sought after service by several builders in India. Sally will soon utilize the 360 views to learn further to improve its object detection accuracy and help with automated valuation.

About Indunia International LLC, the next generation real estate marketplace, is a joint venture between SMC Global, one of the largest financial services company in India with presence in 2400 locations and 500 cities and Software Incubator Inc. a major real estate big data company in USA with 1000 person years of real estate experience. Rooted in consumer life cycle centric user experience design, real estate buyers and sellers experiences this marketplace by searching, learning, playing and getting recommendations about affordable housing and luxury projects/properties, agents/brokers, developers/builders and a variety of service providers such as lenders and arrangers.

About LLC LLC, an Innovation Incubator Inc portfolio company, offers a ground-breaking Real Estate Smart App Development Platform that enables the Real Estate ecosystem to easily consume and monetize data and insights and build Smart Apps. Strategic partners include Software Incubator and Cognub Decision Solutions the first decision science company in Real Estate. Built on industry open standards based Platform as a Service (PaaS) for global scale and bulk sync, empowers users to engage with data, make decisions using insights and build the Real estate future. Headquartered in New York, PropMix also has presence in Boston MA, Leesburg VA, Freehold NJ in USA and Trivandrum, Kerala in India.

Media Contact:Ajith Kavirajan, Indunia International, 7819530902,
Sakeer Hassan, LLC,

Deciphering the lead from the noise

PropMix @ Inman Connect NYC 2017
Deciphering the lead from the noise

Richard Bellamy, CTO at Terradatum
Todd Hoover, SVP at Equifax
Umesh Harigopal, CEO at
Scott Petronis, Chief Product Officer at OnBoard Informatics


With so many leads being generated through multiple inbound channels, Agents and Brokers are at a loss to understand which is a lead that will lead to a transaction, and which ones are just trying to gauge the market without a real intent to transact. How do we enable Real Estate market participants (agents, lenders, mortgage servicers, etc.) decipher the real intent of their customers and focus attention on the leads that are most qualified?


The following major themes emerged from the panel discussion:

  • Inbound marketing via content and research tools are a great way to bring customers to your site, retain them, and then watch their behavior on the site to identify buyers vs. sellers. A typical home purchase takes up to 365 days from intention to transaction and so attracting and retaining a customer and continuing to qualify them is valuable.
  • Chatbots are emerging to engage a consumer, qualify them, and then transition the dialog to a live agent seamlessly. These chatbots are not just talking sentences but offering an immersive experience for the user with video, audio, action prompts, and dialog.
  • Propensity to Sell/Buy/Move predictions are another great way to qualify lead. Machine learning algorithms combine various sources of data – property records, demographics, census, and economic data – to generate such predictions and continue to validate the predictions and learn from real transaction data.

The Propensity to Sell Score combines usage, behaviour, demographic, and economic data to predict how likely a homeowner will be listing their property within a specific time period. The score is a reflection of the confidence in the prediction. With this score, Agents and Brokers can focus on the leads that really matter. This helps them close more transactions faster by dealing with those who are likely to close transactions within a specified period of time.

Millennials leading the way in the global real estate market

PropMix @ Inman Connect NYC 2017
Millennials leading the way in the global real estate market

F. Jacob Cherian, CEO at SMC Global USA Curt Beardsley, VP Industry Development at Zillow Matt Kumar, CEO at Software Incubator Abhimany Anil Londhe, CEO at SMC & IM Capital

There are 2 major shifts happening in the real estate market currently – a large number of millennials are entering the market with a differentiated set of needs and dreams of a home and the real estate market is going global with foreign investment in the US real estate market. A study by Asia Society and Rosen Consulting Group showed that between 2010 and 2015, China alone invested over $93 Billion in the US residential real estate with a growth rate of 20%. India is the second Asian giant to pump over $8 billion into the US real estate market in 2015.

Given these major market shifts Curt provided an excerpt from the Zillow Group’s Research Reports on the influence millennials have in the housing market:

The largest segment of homebuyers in the market today are millennials with the average age of the home buyer at 36.

On the other hand the global nature of the real estate market is driving new technologies to create glocal data bridges to syndicate listings internationally and attract international buyers through the local brick and mortar brokers. SMC Global is one such establishment in India with over 2000 offices across the country to source and deliver buyer leads to agents in the US and vice versa. Non-resident Indians (NRIs) in the US are also investing in the growing Indian real estate market. Regulations in India has improved recently with the implementation of a universal citizen ID card and many property title and valuation specific controls. Online platforms such as Indunia – touted as the Zillow for India – help connect consumers and agents across the globe.

PropMix’s real estate data API platform provides an international listing connector to enable any US real estate portal to display international properties. Similarly the API platform also allows foreign listing portals to support US real estate listings. In addition, every foreign agent can now be an expert at the US real estate market with the PropMix cognitive fabric providing the automated guidance to the agents connecting their customers to the US market.

Cognitive Fabric for Real Estate with new Insights and Instant CMA

MANHASSET HILLS, N.Y., Jan. 17, 2017 /PRNewswire-iReach/ —, an Innovation Incubator portfolio company, announced the general availability of RE CogFab – Real Estate Cognitive Fabric, the first Artificial Intelligence platform-as-a-service for Real Estate. Using the cognitive fabric PropMix is making available new cognitive insights such as Propensity to Sell/Buy, Best Fit Home, and deep analytics for agents and brokers, adding Instant CMA to its next-gen IDX and live CMA app – iCMALive, and providing PropMix Glocal Bridge APIs and international property insights.

RE CogFab is developed in partnership with CogNub Decision Solutions – a cognitive analytics and decision solutions provider. Leveraging the fabric, PropMix has released insights and analytics for agents and brokerages to understand their market performance and competitive positioning, to determine Propensity to Sell/Buy – customers who are going to sell/buy a home soon, and to identify the best fit homes. Propensity to Sell/Buy scores assigned to each home owner helps the agent focus on the leads that really matter. PropMix also announced the availability of variants of its CMA Comps insight such as Best Fit Home, Similar Homes, and Match My Home, all of which enable a user or agent focus on the right homes among the hundreds of listings that are available within a target geography.

“PropMix’s Real Estate Cognitive Fabric will enable us to combine data from various sources – local, listings, public records, and more to generate deeper insights that we can deliver to real estate professionals nationwide.” said Jonathan Bednarsh, President and COO at Onboard Informatics.

The new Instant CMA feature of iCMALive App enables an agent to create an interactive and live CMA report and deliver it to a client in a single click with no manual intervention. Predefined agent specific customizations and branding are automatically incorporated along with a Fair Market Value for the home determined using PropMix’s cognitive insights engine. An automated CMA such as this can be followed up later with a detailed customized CMA report if the lead advances to the next stage in the selling process. This new feature builds on iCMALive’s fundamentally different perspective to CMAs – live CMAs that react to market activity and interactive and collaborative CMAs that engage the seller.

With a strategic partnership with Indunia International, PropMix is enabling non-resident Indians in the US to leverage their local realtor relationship to make investment decisions about properties in India. Similarly, investors in India will be able to invest in the US real estate market using recommendations from big data and cognitive insights.

“We use the PropMix glocal bridge to extend the reach of builders and brokerages who have signed up on our Indunia marketplace. The integration enables us to surface Indian property information and insights to millions of realtors in USA and empower them to leverage the relationship with their local non-resident Indian clients”, said DK Aggarwal Co-founder of Indunia International and Chairman and Managing Director SMC Investment & Advisors. “The integration of PropMix glocal bridge also powers permission based USA property information along with big data and cognitive insights on our marketplace, which enables HNIs in India to make informed real estate investments in USA. PropMix is an ideal solution that has opened up the markets for both Indian and US buyers, brokers and builders”

Realtors will now be able to tap into their local ethnic community relationships by providing property insights across continents in their portals using the PropMix Glocal Bridge API.

“PropMix is leading the new wave of innovation in global housing and mortgage industries by amplifying high value apps that leverages cognitive insights from real estate big data and realtor knowledge”, said Dr. Umesh Harigopal, CEO of LLC. “This strategy will help realtors, brokers, appraisers and lenders become essential as we augment collective human intellect with machine cognition”.

About LLC USA LLC, an Innovation Incubator Inc portfolio company, offers a ground-breaking Real Estate Smart App Development Platform that enables the Real Estate ecosystem to easily consume and monetize data and insights and build Smart Apps. Strategic partners include Software Incubator and Cognub Decision Solutions the first decision science company in Real Estate. Built on industry open standards based Platform as a Service (PaaS) for global scale and bulk sync, empowers users to engage with data, make decisions using insights and build the Real estate future. Headquartered in New York, we also have presence in Boston MA, Leesburg VA, Freehold NJ in USA and Trivandrum, Kerala in India.

Media Contact: Sakeer Hassan,, 7329799507,

Read more about ‘Cognitive Fabric for Real Estate’