Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image processing method and device

An image processing and input image technology, applied in the field of image processing, can solve problems such as inability to image processing

Active Publication Date: 2020-10-27
HANGZHOU HIKVISION DIGITAL TECH
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For computer devices with a small cache, if the above data cannot be accommodated, the image cannot be processed normally

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
  • Image processing method and device
  • Image processing method and device
  • Image processing method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0036] Convolutional neural networks are usually composed of several types of typical layers, such as convolutional layers, pooling layers, fully connected layers, etc. From the perspective of operation, the data involved in the calculation of each layer mainly includes input feature map data and coefficient data (some layers do not have coefficient data, such as pooling layers). The ...

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

The invention relates to an image processing method and device, and belongs to the technical field of machine learning models. The method comprises the following steps: determining data volume limiting conditions respectively corresponding to input image feature data and weight coefficient data of a current layer; determining whether target data of which the data size does not meet a correspondingdata size limiting condition exists in the input image feature data and the weight coefficient data of the current layer, selecting a segmentation dimension for segmenting the target data according to a determination result, and segmenting the target data into data meeting the corresponding data size limiting condition based on the segmentation dimension; and determining output image feature dataof the current layer based on data except the target data in the input image feature data and the weight coefficient data of the current layer and the segmented target data. By adoption of the imageprocessing method and device, even if the cache in the computer device is relatively small, the available storage space is relatively small, and the computer device can normally process the image.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning models, in particular to an image processing method and device. Background technique [0002] With the development of technology, many image processing tasks can be performed by convolutional neural networks. Convolutional neural networks can generally be composed of different types of layers, such as convolutional layers, pooling layers, fully connected layers, etc. Different types of layers have different operation logics, for example, convolution operations are required in convolutional layers. For any layer of the convolutional neural network, the first image feature data can be input into the current layer, the first image feature data and the weight coefficient data in the current layer are subjected to preset calculation processing, and the second image feature data is output after the calculation processing. image feature data. [0003] Images can be processed by convo...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/253Y02D10/00
Inventor 韩新承
Owner HANGZHOU HIKVISION DIGITAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products