Optimizing multi-class image classification using patch features
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A block, image technology, applied in instrumentation, computing, character and pattern recognition, etc., can solve problems such as non-scalability
Active Publication Date: 2017-09-26
MICROSOFT TECH LICENSING LLC
View PDF9 Cites 8 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, using local image features (e.g., HOG) is computationally intensive
Consequently, current techniques for object detection, recognition and / or classification are not scalable and computationally intensive
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0019] Computer vision object (e.g., people, animals, landmarks, etc.), texture, and / or scene classification (e.g., photos, videos, etc.) in images may be useful for including photo and / or video recognition, image search, product related search, etc. Current classification methods include training classifiers based on supervised or labeled data. This approach is not scalable or extensible. Furthermore, current classification methods exploit local image features (e.g., HOG) to learn common sense knowledge (e.g., eyes are part of a person) or specific sub-labels of a general label (e.g., a general label for horse includes subclasses of brown horse, riding horse, etc. Label). However, using local image features (eg, HOG) is computationally intensive. That said, current data mining techniques require a substantial investment in computer resources and are not scalable and / or scalable.
[0020] The technique described in this paper optimizes multi-class image classification by ex...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
Optimizing multi-class image classification by leveraging patch-based features extracted from weakly supervised images to train classifiers is described. A corpus of images associated with a set of labels may be received. One or more patches may be extracted from individual images in the corpus. Patch-based features may be extracted from the one or more patches and patch representations may be extracted from individual patches of the one or more patches. The patches may be arranged into clusters based at least in part on the patch-based features. At least some of the individual patches may be removed from individual clusters based at least in part on determined similarity values that are representative of similarity between the individual patches. The system may train classifiers based in part on patch-based features extracted from patches in the refined clusters. The classifiers may be used to accurately and efficiently classify new images.
Description
Background technique [0001] Computer vision can include object recognition, object classification, object class detection, image classification, etc. Object recognition may describe finding a particular object (eg, a handbag of a particular make, a face of a particular person, etc.). Object classification and object class detection can describe finding objects that belong to a particular classification or class (e.g. faces, shoes, cars, etc.). Image classification can describe the assignment of an entire image to a particular classification or class (eg, place recognition, texture classification, etc.). Computer object recognition, detection, and / or classification using images is challenging because real-world objects vary widely in visual appearance. For example, objects associated with a single label (e.g., cats, dogs, cars, houses, etc.) exhibit diversity in terms of color, shape, size, viewing angle, lighting, etc. [0002] Some current object detection, recognition and...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.