Figure 4 - uploaded by Abdolhossein Sarrafzadeh
Content may be subject to copyright.
Source publication
This paper proposes a novel colour independent Content Based Image Retrieval scheme. Important image information is extracted from visually important areas of image such as edges. Global image features are extracted from the relation among the detailed image information. These two groups of information generate the feature vector. The novel algorit...
Similar publications
In this paper we present an efficient method for Content Based Image Retrieval (CBIR) of occluded images using DCT-phase. The proposed method utilizes a novel correlation metric for ternary-valued DCT-phase, as well as a region merging method to reconstruct the non-occluded regions in the retrieved image. The proposed image retrieval method showed...
The field of image retrieval technologies have enabled the creation of large image datasets. It is necessary to develop appropriate information systems to efficiently manage these collections. An image retrieval system is a computer system for searching, browsing and retrieving images from a large database of images.An approach known as Content-Bas...
This paper presents a novel and an efficient content based image retrieval technique based on content color, texture and shape, which are primary low level features to describe image. The proposed method uses fuzzy texton method to extract texture features and discrete shearlet transform for shape features in addition to color features. Fuzzy Texto...
The problem that we consider in this paper is about the indexing images in a large database. In this context, we propose a new technique for indexing based on the combination of color and shape. This is an improvement of the 2-D histogram method with statistical moments by integrating the shape using Angular Radial Transform (ART) and by applying d...
![Fig. 6 Diagram of AlexNet, the CNN architecture proposed in [18]](publication/343107859/figure/fig3/AS:917413931520000@1595739934204/Diagram-of-AlexNet-the-CNN-architecture-proposed-in-18_Q320.jpg)
Given the great success of Convolutional Neural Network (CNN) for image representation and classification tasks, we argue that Content-Based Image Retrieval (CBIR) systems could also leverage on CNN capabilities, mainly when Relevance Feedback (RF) mechanisms are employed. On the one hand, to improve the performances of CBIRs, that are strictly rel...
Citations
This paper presents a new and effective image indexing technique that extracts features from JPEG compressed images. Using vector quantization techniques (VQ) and a codebook generated using a KK-means clustering algorithm, the proposed technique is able to create an effective histogram from DCT coefficients, which are the major components of JPEG. The proposed method only needs to do partial decoding, therefore it can accelerate the work of indexing images. Experimental results show that its retrieval performance is higher compared with those of other methods from pixel and compressed domains. All experiments confirm the effectiveness and efficiency of the proposed method.
