Spine image recognition method

An image recognition and spine technology, applied in the field of spine image recognition, can solve the problems of being susceptible to interference, poor robustness, and low accuracy.

Active Publication Date: 2015-10-07
GUANGZHOU MEISHI INFORMATION TECH CO LTD
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention proposes a book spine image recognition method to solve the techni

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
  • Spine image recognition method
  • Spine image recognition method
  • Spine image recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0049] see figure 1 , in the present embodiment, the steps of spine image recognition method are as follows:

[0050] 1. Get the spine image

[0051] A mobile smart terminal can be used to take pictures of the spine to obtain a spine image; the shooting environment requires sufficient light and no obvious occlusion, and the number of pixels of each spine should not be less than 1,000 pixels.

[0052] 2. Spine Image Segmentation

[0053] The recognition of the spine image is completed by the image processing module and the recognition and matching module in this embodiment. Before the spine image is recognized, the spine image is firstly segmented, and then the spine visual feature is extracted from the segmented spine image. Finally, the extracted spine visual feature information is used to combine the ISBN library and the spine image library for OCR text recognition and spine image recognition. Visual feature matching.

[0054] When cutting the spine image, a spine cuttin...

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 discloses a spine image recognition method, which comprises the steps of first cutting a spine image; detecting long line segments in the spine image, and finding out and using parallel line segments as a set of parallel long sides of a rectangular selected region; using an iterative algorithm for determining another two short sides of the rectangular selected region when the set of parallel long sides are fixed, and taking the detected rectangular selected region formed by the set of parallel long sides and the two short sides as a cutting result of a spine in the spine image; using a feature extraction algorithm for the cut spine image to describe the spine image into a set of descriptors including the image key point main direction, scale space and Haar wavelet coefficient; and performing feature matching for the spine image in a spine image database through the descriptors, and outputting a plurality of possible spine images corresponding to the spine image to be matched. The invention solves the problems of low accuracy, easy interference and poor robustness in the conventional spine image recognition technology.

Description

technical field [0001] The invention relates to image processing technology, in particular to a method for recognizing book spine images using image processing technology. Background technique [0002] The traditional spine recognition technology usually uses HOUGH transform to detect straight lines to cut the spine. This method can only cut 5-6 books at a time, and when the books are not arranged neatly, the cutting will fail. It can be seen that the traditional spine cutting technology has the disadvantages of low efficiency and poor robustness. In recent years, it has been proposed to use the straight line detection algorithm to detect the edge of the spine, but the detected straight line is not used as prior knowledge in the subsequent iterative operation, resulting in redundant calculations and greatly increasing the calculation amount of the algorithm. The calculation time is too long, which greatly increases the difficulty of the application of the algorithm in reali...

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): G06K9/20G06K9/46G06K9/62
CPCG06V10/22G06V10/462G06V2201/131G06F18/23213
Inventor 吴蔚傅海海肖毅灵夏书予殷策
Owner GUANGZHOU MEISHI INFORMATION 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