New Approach on the Techniques of Content-Based Image Retrieval (CBIR) Using Color, Texture and Shape Features

Abstract

Digital image collection as rapidly increased along with the development of computer network. Image retrieval system was developed purposely to provide an efficient tool for a set of images from a collection of images in the database that matches the user's requirements in similarity evaluations such as image content similarity, edge, and color similarity. Retrieving images based on the content which is color, texture, and shape is called content based image retrieval (CBIR). The content is actually the feature of an image and these features are extracted and used as the basis for a similarity check between images. The algorithms used to calculate the similarity between extracted features. There are two kinds of content based image retrieval which are general image retrieval and application specific image retrieval. For the general image retrieval, the goal of the query is to obtain images with the same object as the query. Such CBIR imitates web search engines for images rather than for text. For application specific, the purpose tries to match a query image to a collection of images of a specific type such as fingerprints image and x-ray. In this paper, the general architecture, various functional components, and techniques of CBIR system are discussed. CBIR techniques discussed in this paper are categorized as CBIR using color, CBIR using texture, and CBIR using shape features. This paper also describe about the comparison study about color features, texture features, shape features, and combined features (hybrid techniques) in terms of several parameters. The parameters are precision, recall and response time.

Image Retrieval Using Auto Encoding Features In Deep Learning

“…The purpose of this article is to assess various image retrieval techniques that focus on extraction of features, description of content, and comparison of content. Shukran et al [7] in their paper examined the various cognitive behavior modification (CBIR) techniques classified as colorbased, texture-based, shape-based, and hybrid-based. It also provides a comparative analysis of color-based features, texture-based features, and hybrid techniques, using multiple parameters such as precision, recall, and response time.. Yu Zhao [8] focused on the statistical feature approach of the double-Tree complex wavelet was initially developed to recover edge information in document images by combining the statistical characteristic method with the human eye's visual features.…”

“…Prior to image processing, preprocessing is employed to eliminate distortions [7] and other unwanted components, as well as to extract the correct part of the image. It entails a variety of processes and techniques performed to a picture to improve its quality, decrease noise, and get it ready for more processing or analysis.…”

Hybrid Bag-of-Visual-Words and FeatureWiz Selection for Content-Based Visual Information Retrieval

“…Many research papers overviewed CBIR [ 5 , 6 , 7 , 8 , 9 ]. Recently, the image features have been based on color, texture, and shape to quantify image content [ 10 , 11 , 12 ]. Then, various algorithms were developed to describe the features of the image.…”

Absent Color Indexing: Histogram-Based Identification Using Major and Minor Colors

“…Proposed image features for pattern search have included gray features [1], texture features [2], color features [3], and convolution features [4], where color features provide universally successful cues for identification of individuals in many applications. These have been extensively utilized in pattern search, computer vision, and image processing [5][6][7]. Analysis of color features plays a vital role in various tasks, including object matching, background subtraction, video tracking, and image retrieval [8][9][10].…”