Age and gender evaluation based on small-scale convolutional neural network for embedded system

A convolutional neural network, small-scale technology, applied in the field of machine learning and artificial intelligence, can solve the problems of extra computing overhead, face detection and face alignment inherent correlation neglect, and achieve the effect of reducing operating costs

Active Publication Date: 2018-04-13
SHENZHEN ALTUMVIEW TECH CO LTD
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Note that each stage of bounding box correction within a cascaded CNN requires additional computational overh

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
  • Age and gender evaluation based on small-scale convolutional neural network for embedded system
  • Age and gender evaluation based on small-scale convolutional neural network for embedded system
  • Age and gender evaluation based on small-scale convolutional neural network for embedded system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0056] The following detailed description is intended as a description of various configurations of the subject technology, and is not intended to represent the only configuration in which the subject technology can be implemented. The drawings are included in this text and form part of the detailed description. The detailed description includes specific details intended for a comprehensive understanding of the subject technology. However, the subject technology is not limited to the specific details described in this article, and it may be implemented without these specific details. In some cases, the structure and components are shown in the form of block diagrams to avoid obscuring the concept of the subject technology.

[0057] Throughout the specification, unless the context clearly dictates otherwise, the following terms have the meanings provided here. The terms "image resolution" and "image size" are interchangeable and are used to refer to the number of pixels in a giv...

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

Embodiments described herein provide a plurality of examples that can perform an age and gender evaluation system on a face image, the size of the face image being greater than the maximum of input pixels supportable by a given small-scale convolutional neural network (CNN) module. In some embodiments, the age and gender evaluation system firstly divides the high-resolution input face image into agroup of image blocks having suitable sizes, and a precisely-designed overlapping portion is disposed between the adjacent image blocks. Then each image block is respectively processed by the small-scale CNN module, such as an embedded CNN module of a Hi3519 SoC. Outputs corresponding to the group of image blocks are subsequently combined so as to obtain an output of the input face image, the combined outputs can be further processed by a subsequent layer of the age and gender evaluation system, and age and gender classification is generated for the input face image.

Description

[0001] Priority claims and related patent applications [0002] This patent application claims U.S. Provisional Patent Application 62 / 428,497 (Title: CONVOLUTIONAL NEURALNETWORKS (CNN) BASED ON RESOLUTION-LIMITED SMALL-SCALE CNN MODULES); inventors: Wang Xing, Wu Qianwei, Liang Jie; filing date: November 30, 2016) priority. The content of this US provisional application is incorporated by reference into and made a part of this application. [0003] This application is also related to pending US patent application 15 / 441,194 (Application Title: CONVOLUTIONAL NEURAL NETWORK (CNN) SYSTEMBASED ON RESOLUTION-LIMITED SMALL-SCALE CNN MODULES); inventors: Wang Xing, Wu Qianwei, Liang Jie; application date: February 23, 2017). This US patent application is incorporated by reference and made a part of this application. This application is also related to pending U.S. patent application 15 / 657,109 (application title: FACE DETECTION USING SMALL-SCALE CONVOLUTIONAL NEURAL NETWORK (CNN) M...

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): G06K9/00G06K9/46G06K9/62G06N3/04
CPCG06V40/178G06V40/172G06V10/454G06N3/045G06F18/2148G06F18/24
Inventor 王星梅迪·塞伊菲陈明华吴谦伟梁杰
Owner SHENZHEN ALTUMVIEW TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap