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

Large-scale target identification method based on mobile platform

A target recognition and mobile platform technology, applied in the field of image recognition, can solve problems such as no longer applicable image retrieval

Active Publication Date: 2015-03-04
JILIN UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, with the development of the network, the use of high-dimensional features in the form of floating-point numbers such as SIFT is no longer suitable for image retrieval on mobile devices.

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
  • Large-scale target identification method based on mobile platform
  • Large-scale target identification method based on mobile platform
  • Large-scale target identification method based on mobile platform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] Embodiment 1: First, some concepts in the description of the implementation steps are explained.

[0107] 1. Implementation steps of the training process

[0108] 1. First obtain the SIFT descriptor of each image in the image dataset.

[0109] 2. For the set of descriptors of all images in the data set, use the k-means iterative method to minimize the objective function: NS + MD. At the end of this process, we will have binary label information adapted to the distribution properties of the data points in Euclidean space.

[0110] 3. For datasets, divide the datasets into different groups according to their label information. Each group can get a weak hash function.

[0111] 4. Use the AdaBoost mechanism to combine weak hash functions into a strong hash function, further emphasizing that the resulting binary code can maintain the proximity between data points. The resulting binary code can approximately replace the Euclidean distance between data points. An inver...

Embodiment 2

[0126] Datasets: Two popular datasets are used as the retrieved datasets, namely the SIFT1M dataset and the CIFAR10 dataset. Among them, the SIFT1M data set contains a total of 1 million training data sets and 100,000 test data sets. While CIFAR10 contains 60,000 images. 50,000 images are used as the training set and 10,000 images are used as the test set. They all use Top-10as a measure of accuracy.

[0127] Evaluation index: use the general average retrieval accuracy ( mAP ), recall rate and average retrieval time to test the present invention and other best methods in the industry for comparison.

[0128] In the CIFAR10 data set, the feature descriptors of the training data set and the test data set are extracted through the SIFT algorithm. Under the two data sets respectively, use the present invention and the best methods in the industry (KMH[3], ITQ[4], RR[6], LSH[9], SH[5]) to retrieve the test data set respectively in the training nearest neighbors in the datas...

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 belongs to the field of image recognition and aims to provide a quick and effective large-scale target identification method based on a mobile platform for mobile platform search, and the method can be used for quickly and effectively encoding SIFT (scale invariant feature transform) characteristic points into binary codes with a function of keeping local sensitivity by a Hash algorithm. The method comprises the following steps: obtaining label information of SIFI characteristics X of a database image, wherein the label information consists of '0' and '1'; defining normalized distance similarity and quantization errors; searching a binary label of a data point with minimum value of the sum of NS and MD; obtaining weak Hash functions; combining the weak Hash functions to obtain a strong Hash function. The method is a quick and effective mobile platform search method; the search scheme of mobile equipment can be adjusted according to network conditions, so that responses can be given in time under different network conditions.

Description

technical field [0001] The invention belongs to the field of image recognition. Background technique [0002] In recent years, the nearest neighbor retrieval problem has been widely applied to image retrieval problems, such as image retrieval on mobile devices. However, with the development of the network, the use of high-dimensional features in the form of floating-point numbers such as SIFT is no longer suitable for image retrieval on mobile devices. To solve this problem, people began to use compact binary codes to represent feature descriptors more widely. When the retrieval is performed using binary code, the data structure is simpler and the retrieval speed is faster. [0003] Andoni proposed a locality-sensitive hash algorithm, which is a relatively simple classic algorithm, and the hash function of the algorithm is a randomly generated mapping plane. The hash function has nothing to do with the data. As the number of encoding bits increases, the performance of the...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/30G06K9/66
CPCG06F16/583G06V10/462
Inventor 刘萍萍赵宏伟王振李清亮臧雪柏于繁华戴金波耿庆田
Owner JILIN UNIV
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