Computer vision assisted item search

Abstract

System and techniques for computer vision assisted item search are described herein. A composite image, including visual data and depth data, may be obtained. The composite image may be filtered to isolate a clothing article represented in the composite image. A classifier may be applied to the depth data to produce a set of clothing attributes for the clothing article. The clothing attributes may then be provided to a remote device.

1 . (canceled) 
     
     
         2 . A system for computer vision assisted item search, the system comprising:
 a hardware interface to obtain a depth image from a sensor;   a classifier to produce a set of clothing attributes, from the depth image, that correspond to a clothing article in the depth image, the set of clothing attributes including a texture; and   a transceiver to provide the clothing attributes to a receiver.   
     
     
         3 . The system of  claim 2 , wherein the sensor is in a sensor array, and wherein the classifier is at a computing system remote from the sensor array. 
     
     
         4 . The system of  claim 2 , wherein the set of clothing attributes include at least one of a size, or a shape. 
     
     
         5 . The system of  claim 4 , wherein the set of clothing attributes include a fabric derived from the depth image by the classifier. 
     
     
         6 . The system of  claim 4 , wherein the set of clothing attributes include a clothing type, and wherein the classifier is to:
 scale a representation of the clothing article from the depth image using depth data to produce an estimate of absolute measurements of the clothing article; and   convert the estimate of absolute measurements to a clothing article size.   
     
     
         7 . The system of  claim 2 , wherein a color image is obtained by the hardware interface, the color image corresponding to the depth image, wherein the classifier is to add to the clothing attributes by classifying the color image, and wherein added clothing attributes include at least one of a color or a pattern. 
     
     
         8 . The system of  claim 7 , comprising a search engine, the search engine to search for additional clothing items using the clothing attributes and a user profile. 
     
     
         9 . The system of  claim 8 , wherein to search for additional clothing items includes the search engine to apply a restriction that the additional clothing items differ from the clothing article in at least one of color, pattern, style, or type. 
     
     
         10 . The system of  claim 9 , wherein the additional clothing items differ in type, and wherein the additional clothing items are filtered to combine with the clothing article to add to a class of outfits. 
     
     
         11 . The system of  claim 8 , wherein the search engine is to provide the search results to a third party. 
     
     
         12 . At least one non-transitory machine readable medium including for computer vision assisted item search, the instructions, when executed by processing circuitry, cause the processing circuitry to perform operations comprising:
 obtaining a depth image from a sensor;   applying a classifier to the depth image to produce a set of clothing attributes that correspond to a clothing article in the depth image, the set of clothing attributes including a texture; and   transmitting the clothing attributes to a receiver.   
     
     
         13 . The at least one non-transitory machine readable medium of  claim 12 , wherein the sensor is in a sensor array, and wherein the classifier is at a computing system remote from the sensor array. 
     
     
         14 . The at least one non-transitory machine readable medium of  claim 12 , wherein the set of clothing attributes include at least one of a size, or a shape. 
     
     
         15 . The at least one non-transitory machine readable medium of  claim 14 , wherein the set of clothing attributes include a fabric derived from the depth image by the classifier. 
     
     
         16 . The at least one non-transitory machine readable medium of  claim 14 , wherein the set of clothing attributes include a clothing type, wherein the classifier scales a representation of the clothing article from the depth image using depth data to produce an estimate of absolute measurements of the clothing article, and wherein the estimate of absolute measurements is converted to a clothing article size. 
     
     
         17 . The at least one non-transitory machine readable medium of  claim 12 , wherein a color image is obtained by the hardware interface, the color image corresponding to the depth image, wherein the classifier is to add to the clothing attributes by classifying the color image, and wherein added clothing attributes include at least one of a color or a pattern. 
     
     
         18 . The at least one non-transitory machine readable medium of  claim 17 , wherein the operations include using a search engine to search for additional clothing items using the clothing attributes and a user profile. 
     
     
         19 . The at least one non-transitory machine readable medium of  claim 18 , wherein searching for the additional clothing items includes restricting the additional clothing items to those that differ from the clothing article in at least one of color, pattern, style, or type. 
     
     
         20 . The at least one non-transitory machine readable medium of  claim 19 , wherein the additional clothing items differ in type, and wherein the additional clothing items are filtered to combine with the clothing article to add to a class of outfits. 
     
     
         21 . The at least one non-transitory machine readable medium of  claim 18 , wherein the search results are provided to a third party.