Investigation into Computer vision methods to extract information for Context based image retrieval methods

2011 ◽  
pp. 123-135
Author(s):  
Karen Le Roux
Keyword(s):  
Computer Vision ◽  
Image Retrieval ◽  
Extract Information

scholarly journals Image Retrieval Based on Fractal Dictionary Parameters

2013 ◽  
Vol 2013 ◽  
pp. 1-8
Author(s):  
Yuanyuan Sun ◽  
Rudan Xu ◽  
Lina Chen ◽  
Xiaopeng Hu
Keyword(s):  
Computer Vision ◽  
Image Compression ◽  
Image Retrieval ◽  
Experimental Results ◽  
Content Based Image Retrieval ◽  
Efficient Management ◽  
Retrieval Rate ◽  
Statistical Indices ◽  
Visual Database

Content-based image retrieval is a branch of computer vision. It is important for efficient management of a visual database. In most cases, image retrieval is based on image compression. In this paper, we use a fractal dictionary to encode images. Based on this technique, we propose a set of statistical indices for efficient image retrieval. Experimental results on a database of 416 texture images indicate that the proposed method provides a competitive retrieval rate, compared to the existing methods.

scholarly journals Transformers in Pedestrian Image Retrieval and Person Re-Identification in a Multi-Camera Surveillance System

2021 ◽  
Vol 11 (19) ◽  
pp. 9197
Author(s):  
Muhammad Tahir ◽  
Saeed Anwar
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Object Recognition ◽  
Image Retrieval ◽  
Surveillance System ◽  
Input Image ◽  
Benchmark Datasets ◽  
Overall Performance ◽  
Camera Surveillance ◽  
Surveillance Applications

Person Re-Identification is an essential task in computer vision, particularly in surveillance applications. The aim is to identify a person based on an input image from surveillance photographs in various scenarios. Most Person re-ID techniques utilize Convolutional Neural Networks (CNNs); however, Vision Transformers are replacing pure CNNs for various computer vision tasks such as object recognition, classification, etc. The vision transformers contain information about local regions of the image. The current techniques take this advantage to improve the accuracy of the tasks underhand. We propose to use the vision transformers in conjunction with vanilla CNN models to investigate the true strength of transformers in person re-identification. We employ three backbones with different combinations of vision transformers on two benchmark datasets. The overall performance of the backbones increased, showing the importance of vision transformers. We provide ablation studies and show the importance of various components of the vision transformers in re-identification tasks.

scholarly journals Frontiers of Computer Vision Technologies on Real Estate Property Photographs and Floorplans

2021 ◽  
pp. 325-337
Author(s):  
Yoji Kiyota
Keyword(s):  
Artificial Intelligence ◽  
Computer Vision ◽  
Deep Learning ◽  
Real Estate ◽  
Image Data ◽  
Learning Technologies ◽  
Data Sets ◽  
Academic Communities ◽  
Estate Property ◽  
Extract Information

AbstractThis article describes frontier efforts to apply deep learning technologies, which is the greatest innovation of research on artificial intelligence and computer vision, to image data such as real estate property photographs and floorplans. Specifically, attempts to detect property photographs that violate regulations or were misclassified, or to extract information that can be used as new recommendation features from property photographs, were mentioned. Besides, this article introduces an innovation created by providing data sets for academic communities.

scholarly journals Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering

2019 ◽  
Vol 33 ◽  
pp. 8134-8141 ◽  
Author(s):  
Binghui Chen ◽  
Weihong Deng
Keyword(s):  
Computer Vision ◽  
Image Retrieval ◽  
Metric Learning ◽  
Regularization Technique ◽  
Generalization Ability ◽  
Regularization Term ◽  
Deep Metric Learning

Deep metric learning has been widely applied in many computer vision tasks, and recently, it is more attractive in zeroshot image retrieval and clustering (ZSRC) where a good embedding is requested such that the unseen classes can be distinguished well. Most existing works deem this ’good’ embedding just to be the discriminative one and thus race to devise powerful metric objectives or hard-sample mining strategies for leaning discriminative embedding. However, in this paper, we first emphasize that the generalization ability is a core ingredient of this ’good’ embedding as well and largely affects the metric performance in zero-shot settings as a matter of fact. Then, we propose the Energy Confused Adversarial Metric Learning (ECAML) framework to explicitly optimize a robust metric. It is mainly achieved by introducing an interesting Energy Confusion regularization term, which daringly breaks away from the traditional metric learning idea of discriminative objective devising, and seeks to ’confuse’ the learned model so as to encourage its generalization ability by reducing overfitting on the seen classes. We train this confusion term together with the conventional metric objective in an adversarial manner. Although it seems weird to ’confuse’ the network, we show that our ECAML indeed serves as an efficient regularization technique for metric learning and is applicable to various conventional metric methods. This paper empirically and experimentally demonstrates the importance of learning embedding with good generalization, achieving state-of-theart performances on the popular CUB, CARS, Stanford Online Products and In-Shop datasets for ZSRC tasks. Code available at http://www.bhchen.cn/.

Comparison of Color, Texture and ICM Features in CBIR System

2011 ◽  
Vol 403-408 ◽  
pp. 13-19 ◽  
Author(s):  
Sonali Bhadoria ◽  
Meenakshi Madugunki ◽  
C.G. Dethe ◽  
Preeti Aggarwal
Keyword(s):  
Computer Vision ◽  
Image Retrieval ◽  
Data Base ◽  
Image Databases ◽  
Content Based Image Retrieval ◽  
Retrieval Process ◽  
Retrieval Performance ◽  
Research Areas ◽  
Matching Techniques ◽  
Index Search

Image retrieval has been one of the most interesting and vivid research areas in the field of computer vision over the last decades. Content-Based Image Retrieval (CBIR) systems are used in order to automatically index, search, retrieve, and browse image databases. There are various features which can be extracted from the image which gives different performance in retrieving the image.al systems. In this paper we have tried to compare the effect of using different features on the same data base to implement CBIR system. We have tried to analyse the retrieval performance for each feature. We have compared different features as well as the combinations of them to improve the performance. We have also compared the effect of different matching techniques on the retrieval process.

scholarly journals Content-Based Image Retrieval and Feature Extraction: A Comprehensive Review

2019 ◽  
Vol 2019 ◽  
pp. 1-21 ◽  
Author(s):  
Afshan Latif ◽  
Aqsa Rasheed ◽  
Umer Sajid ◽  
Jameel Ahmed ◽  
Nouman Ali ◽  
...  
Keyword(s):  
Computer Vision ◽  
Feature Extraction ◽  
Image Retrieval ◽  
Image Classification ◽  
Image Representation ◽  
Feature Representation ◽  
Image Feature ◽  
Content Based Image Retrieval ◽  
Comprehensive Review ◽  
Visual Understanding

Multimedia content analysis is applied in different real-world computer vision applications, and digital images constitute a major part of multimedia data. In last few years, the complexity of multimedia contents, especially the images, has grown exponentially, and on daily basis, more than millions of images are uploaded at different archives such as Twitter, Facebook, and Instagram. To search for a relevant image from an archive is a challenging research problem for computer vision research community. Most of the search engines retrieve images on the basis of traditional text-based approaches that rely on captions and metadata. In the last two decades, extensive research is reported for content-based image retrieval (CBIR), image classification, and analysis. In CBIR and image classification-based models, high-level image visuals are represented in the form of feature vectors that consists of numerical values. The research shows that there is a significant gap between image feature representation and human visual understanding. Due to this reason, the research presented in this area is focused to reduce the semantic gap between the image feature representation and human visual understanding. In this paper, we aim to present a comprehensive review of the recent development in the area of CBIR and image representation. We analyzed the main aspects of various image retrieval and image representation models from low-level feature extraction to recent semantic deep-learning approaches. The important concepts and major research studies based on CBIR and image representation are discussed in detail, and future research directions are concluded to inspire further research in this area.

Color Space Comparison between RGB and HSV Based Images Retrieval

2014 ◽  
Vol 989-994 ◽  
pp. 4123-4126 ◽  
Author(s):  
Ching Hung Su ◽  
Huang Sen Chiu ◽  
Jui Hung Hung ◽  
Tsai Ming Hsieh
Keyword(s):  
Computer Vision ◽  
Image Retrieval ◽  
Color Space ◽  
Human Perception ◽  
Visual Attributes ◽  
Retrieval Problem ◽  
Comparison And Analysis

The visual attributes of color are suitable for human perception and computer vision. A Color space is defined as a model for representing the intensity value of color. We propose a color space comparison and analysis between RGB and HSV based images retrieval. We succeed in transferring the image retrieval problem to sequences comparison and subsequently using the color sequences comparison between the color featurs of RGB and HSV to compare and analyze the images of database.

scholarly journals Integration of Statistical based Texture and Color Feature for Medical Image Retrieval

2019 ◽  
Vol 8 (3) ◽  
pp. 5584-5588 ◽  
Keyword(s):  
Computer Vision ◽  
Pattern Recognition ◽  
Image Retrieval ◽  
Medical Image ◽  
Spatial Information ◽  
Image Database ◽  
Content Based Image Retrieval ◽  
Retrieval Method ◽  
Medical Image Retrieval ◽  
The Common

Today, the common problem in the domain of computer vision and pattern recognition is content based image retrieval (CBIR). In this paper, a novel image retrieval method using the geometric details based on the correlation among edgels and correlation between pixels has been introduced. The autocorrelation based choridiogram descriptor has been extracted from the image to obtain geometric, texture and spatial information. Color autocorrelogram has been computed to obtain color, texture and spatial information. The proposed method is tested on benchmark heterogeneous medical image database and LIDC-IDRI-CT and VIA/I-ELCAP-CT databases and results are compared with typical CBIR system for medical image retrieval

scholarly journals Feature Fusion for Image Retrieval using Image Processing

2019 ◽  
Vol 8 (12) ◽  
pp. 3157-3162
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Image Retrieval ◽  
Principle Component Analysis ◽  
Clustering Algorithm ◽  
Feature Fusion ◽  
The Other ◽  
Content Based Image Retrieval ◽  
Huge Amount ◽  
Attribute Data

Image processing and computer vision uses Content-based image retrieval (CBIR) function to solve the issue of image retrieval, which means, solving the issue of image searching in expansive databases. The actual data of the image will be evaluated when a search is performed that refers to content-based. The term content can be any attribute of an image like colour-shade, various symbols or shapes, sizes, or any other data. There are various approaches for image retrieval but the most prominent are by comparing the main image with the subsets of the relatable images whether it matches or not and the other one is by using a matching descriptor for the image. One of the main trouble for huge amount of CBIR is the representation of an image. When a given image is worked upon it is divided into number of attributes in which some are the primary ones and others are the secondary ones. These attributes are checked with the local and MPEG-7 descriptors. All this is then mapped in a single vector which is the same images but in compact form to save the space. Principle Component Analysis (PCA) is used lessen the attribute size. To store the attribute data in similar clusters and to train them to give the correct output the study also uses k-means clustering algorithm. Hence, the proposed system deals with the image retrieval using various algorithms and methods.

Sign in / Sign up

Export Citation Format

Share Document