Unlock instant, AI-driven research and patent intelligence for your innovation.

Systems and methods for providing an image classifier

A technology in images and images, applied in the field of high-efficiency image classification, can solve the problems of loss of matching accuracy and limited practicality of mobile implementation methods, and achieve the effect of increasing efficiency

Active Publication Date: 2018-11-09
MOVIDIUS LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0022] While it is possible to subsample the input image and perform a series of optimizations for mobile platforms, this often comes at a huge loss in matching accuracy, resulting in very limited practicality for mobile implementations

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
  • Systems and methods for providing an image classifier
  • Systems and methods for providing an image classifier
  • Systems and methods for providing an image classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] In the following description, numerous specific details are set forth regarding the systems and methods of the disclosed subject matter, the environments in which these systems and methods may operate, etc., in order to provide a thorough understanding of the disclosed subject matter. It will be apparent, however, to those skilled in the art that the disclosed subject matter may be practiced without these specific details and certain features that are known in the art have not been described in detail in order to avoid obscuring the disclosed subject matter. Additionally, it should be understood that the examples provided below are exemplary and that it is contemplated that there are other systems and methods within the scope of the disclosed subject matter.

[0048] The present invention utilizes conditional processing using a bitmap that encodes those portions of the image that are used to train the classifier. Bitmaps are exported by any suitable means. For example,...

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

No PUM Login to View More

Abstract

Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.

Description

technical field [0001] This application relates generally to computer vision processing, and more specifically to efficient image classification. Background technique [0002] The field of computer vision often requires classifiers trained to detect objects such as faces and people, allowing for applications that interact with people and real-world objects. Various classifiers exist because computer vision researchers are always looking for more resource-efficient ways to accurately locate and identify various objects in images. [0003] One known method of recognizing objects of a particular class, depicted in Figure 1, uses Histograms of Oriented Gradients (HoG) in combination with training images and a learning system. HoG has been used to detect humans against a variety of backgrounds, as well as faces, animals, vehicles, and other objects. Since HoG uses relatively compact reference descriptors, it has been successfully used to classify objects in streaming video in r...

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
no application Login to View More
IPC IPC(8): G06K9/46G06K9/62
CPCG06F18/2411G06F18/214G06V40/103G06V10/955G06V10/507G06V40/172G06F18/28G06V30/194G06V10/7557G06V10/50G06V10/758
Inventor D·莫洛尼A·德加尼
Owner MOVIDIUS LTD