Content-Based Image Retrieval using color and shape descriptors

Pujari, Jagadeesh; Pushpalatha, S.; Padmashree, D.

doi:10.1109/icsip.2010.5697476

Cited by 23 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It is very important to remove noise from the image to get good results in the retrieval images. The proposed method consist of three stages: in the first stage, after converting RGB image to HSV image, the HSV color quantization is implemented using color histogram with quantization schemes (8,8,8). The color features are extracted according to HSV histogram values.…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Image Retrieval using Multi Cascaded Features

Jehlol¹,

Gailan²,

Oleiwi³

2016

IJCA

View full text Add to dashboard Cite

This paper depends on Content Based Image Retrieval CBIR to retrieve desired images from a large images database. It is based on extracting cascade features from image such as color, shape and texture features. The Euclidean Distance is used to measure similarity of each feature and retrieve similar images from the image database. The proposed method contains three stages: in the first stage, the HSV color histogram from query image is found and the nearest 100 images are retrieved. In the second stage the shape features are extracted from edge detection and the nearest 50 image are retrieved. In the last stage the texture feature are found based on first order features and the nearest 10 images are retrieved. In this paper a mechanism for image retrieval based on cascading approach is developed to improve image retrieval performance and reduce the computational time required to retrieve images. It is found that cascading features with Euclidean distance give about 76% precession of image retrieval.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…Pujari J. et al [8]. Proposed a novel method based on color and shape features that used various extracted components from the images such as Lab and HSV.…”

Section: Related Workmentioning

confidence: 99%

Image Retrieval using Multi Cascaded Features

Jehlol¹,

Gailan²,

Oleiwi³

2016

IJCA

View full text Add to dashboard Cite

show abstract

“…Van et al [20] studied the invariance properties and the distinctiveness of colour descriptors based on SIFT and Histograms, in which, apart from object recognition, the descriptors can be used for content-based image retrieval (CBIR) systems to search for similar images. Pujari et al [51] presented a framework which uses colour and shape features from Lab and HSV spaces to retrieve edge features, and the experiments carried out in the Corel dataset demonstrated the efficiency of the method. Alzu et al [52] introduced an optimized image descriptor that combines colour histogram in HSV space with the rootSIFT [53] descriptors and outperformed many state-of-the-art methods.…”

Section: B Colour Descriptorsmentioning

confidence: 99%

Colour Neural Descriptors for Instance Retrieval Using CNN Features and Colour Models

et al. 2021

View full text Add to dashboard Cite

Image representations in the form of neural activations derived from intermediate layers of deep neural networks are the state-of-the-art descriptors for instance based retrieval. However, the problem that persists consists of how to retrieve identical images as the most relevant ones from a large image or video corpus. In this work, we introduce colour neural descriptors that are made of convolutional neural networks (CNN) features obtained by combining different colour spaces and colour channels. In contrast to previous works, which rely on fine-tuning pre-trained networks, we compute the proposed descriptors based on the activations generated from a pretrained VGG-16 network without fine-tuning. Besides, we take advantage of an object detector to optimize our proposed instance retrieval architecture to generate features at both local and global scales. In addition, we introduce a stride based query expansion technique to retrieve objects from multi-view datasets. Finally, we experimentally proved that the proposed colour neural descriptors, obtain state-of-the-art results in Paris 6K, Revisiting-Paris 6k, INSTRE-M and COIL-100 datasets, with mAPs of 81.70, 82.02, 78.8 and 97.9, respectively.

show abstract

“…For any other approaches different color values gets importance. Jagadeesh Pujari, Pushpalatha S.N, Padmashree D.Desai [5] used HSV and Lab color space to recognize an image and then compared it with gray and RGB approach. In their experiment Lab color space gives better result than other ones.…”

Section: Realted Workmentioning

confidence: 99%

Content based Natural Image Retrieval using Histogram, Segmentation and Edge

Safikul¹,

Mukherjee²

2018

IJCA

View full text Add to dashboard Cite

Content Based Image Retrieval (CBIR) is a process to retrieve a stored image from database by supplying an image as query instead of text. This can be done by proper feature extraction and querying process. The features like histogram, color values and edge detection plays very vital role in proper image retrieval. Here we have implemented a method of image retrieval using the histogram, color and edge detection features. In this method we used image segmentation in order to get a better accuracy percentage and this proved itself to be a very successful approach. We used our own computation method as well as some MATLAB functions. Canny's edge detection technique and color values extraction after image segmentation gives a better accuracy level to our system. Finally we get top images matching to our query image using Euclidean distance.

show abstract

Content-Based Image Retrieval using color and shape descriptors

Cited by 23 publications

References 4 publications

Image Retrieval using Multi Cascaded Features

Image Retrieval using Multi Cascaded Features

Colour Neural Descriptors for Instance Retrieval Using CNN Features and Colour Models

Content based Natural Image Retrieval using Histogram, Segmentation and Edge

Contact Info

Product

Resources

About