Convolutional-neural-network-based image feature extraction method and system
A convolutional neural network and image feature extraction technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problems of reducing the accuracy of image extraction, long time for image extraction, and low extraction efficiency, and achieves the goal of overcoming color inconsistencies. Effects of sensitive defects, shortened image extraction time, and improved extraction efficiency
Inactive Publication Date: 2017-03-08
上海影城有限公司
View PDF1 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most of the current image feature processing methods need manual preprocessing, and the image extraction feature method is not sensitive to color, which reduces the accuracy of image extraction; it takes a long time to extract pictures and the extraction efficiency is low
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.
[0054] as attached figure 1 As shown, the present invention provides a kind of image feature extraction method based on convolutional neural network, comprises the steps:
[0055] Step 1. Image acquisition step: acquire an image to be processed, wherein the image to be processed is a color image;
[0056] Step 2, preprocessing step: preprocessing the image to be processed to obtain a preprocessed image;
[0057] Step 3, image area extraction step: extracting a specified area from the preprocessed imag...
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
The invention provides a convolutional-neural-network-based image feature extraction method and system. The method comprises: a to-be-processed image is obtained, wherein the to-be-processed image is a color image; pretreatment is carried out on the to-be-processed image to obtain an image after pretreatment; a designated region is extracted from the image after pretreatment and is used as a designated dimension image; a color feature vector is extracted from the designated dimension image; the color feature vector is inputted into a convolutional neural network and the output of the convolutional neural network is used as a first feature vector; and according to the color feature vector and the first feature vector, an image feature vector is obtained. Besides, module functions of the system correspond to the method. The method and system have the following advantages: after image pretreatment, too much manual pretreatment on an inputted image is not required; because of the core feature extraction, picture extraction time is shortened and the extraction efficiency is improved; and a defect that the feature extraction method is not sensitive to colors is overcome, thereby improving the extraction accuracy.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to an image feature extraction method and system based on a convolutional neural network in the technical field of image classification. Background technique [0002] Convolutional neural network is a feed-forward neural network. Its artificial neurons can respond to surrounding units within a part of the coverage area, and it has excellent performance for large-scale image processing. It includes convolutional and pooling layers. Convolutional neural network has translation and scale invariance for image processing, so it is widely used in image feature extraction. Most of the current image feature processing methods require manual preprocessing, and the image extraction feature method is not sensitive to color, which reduces the accuracy of image extraction; it takes a long time to extract pictures and the extraction efficiency is low. Contents of the invention...
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
Login to View More IPC IPC(8): G06T7/11G06T7/90
CPCG06T2207/20084
Inventor 顾艳余金龙沈宁宇
Owner 上海影城有限公司