Using Color Strings Comparison for Video Frames Retrieval

Lin, Chiunhsiun; Su, Ching-Hung

doi:10.1109/icimt.2009.30

Cited by 8 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the work in hand, we implemented a new color coding technique to represent the image features, then the meta-heuristic algorithms for image retrieval. This new approach which is based on the color string coding method will increase the number of relevant images and improve the response and execution time of the previous methods [15]. The proposed CBIR system is presented in Figure 2.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Then, they performed an unsupervised machine learning clustering to avoid the search for matching similarity in the whole image dataset. Lin et al [15] applied the color string comparison after converting the video frames to a color string. In Jenni et al [16], all the images in the database are classified into different groups using support vector machine, then the image retrieval is done based on a simple similarity measure between strings representing images.…”

Section: Related Workmentioning

confidence: 99%

“…After creating these three matrices, we compare them element by element to determine the color value that will be taken to create the final matrix which contains the strongest intensities. The previous method [15], [16], determines six criteria for coding colors. This method does not specify some exceptional cases, and it can assign two characters for the same color series.…”

Section: Color String Codingmentioning

confidence: 99%

“…To avoid being trapped in the local optima, we accept to move to the neighbour solution (x') despite the increase of the energy level (δE). Whether, this change in the solution is accepted or rejected based on a probability called acceptance function as presented in (15).…”

Section: Description Of the Simulated Annealing Algorithmmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Content Based Image Retrieval Based on a New Approach of Color String Coding and Meta-Heuristic Algorithms

Machhour¹

2020

IJATCSE

View full text Add to dashboard Cite

Content based image retrieval (CBIR) is ranked among the most important domain of image processing. This technique allows us to find the relevant images from a query image in a very large image database. This approach is based on the visual features of the image. Therefore, the choice of these features is a very decisive factor for improving the robustness and efficiency of the CBIR system. This paper aims at the development of a novel technique which is based on the color string coding method implemented in the previous work. This new technique combines the two color spaces: RGB and HSV, and introduces the texture features to improve the results obtained previously by increasing the number of relevant images and decreasing the computational complexity and the response time whatever the size of the images. Accordingly, the image retrieval is performed using the meta-heuristic algorithms. Meanwhile, our system is evaluated based on the precision and recall measures. The obtained results show the efficiency and the performance of the proposed method compared to other CBIR systems.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Color String Codingmentioning

confidence: 99%

Section: Description Of the Simulated Annealing Algorithmmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Content Based Image Retrieval Based on a New Approach of Color String Coding and Meta-Heuristic Algorithms

Machhour¹

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…We will use this features inside a classification tool. In this paper, we can use the colour string coding and comparison [23] for efficient CBIR. We extract the features for query image and all images in database.…”

Section: B Feature Extractionmentioning

confidence: 99%

Content Based Image Retrieval Using Colour Strings Comparison

Jenni

Mandala

Sunar

2015

Procedia Computer Science

View full text Add to dashboard Cite

Content Based Image Retrieval (CBIR) is a technique that enables a user to extract an image based on a query, from a database containing a large amount of images. A very fundamental issue in designing a content based image retrieval system is to select the image features that best represent the image contents in a database. In this paper, our proposed method mainly concentrated on database classification and efficient image representation. We present a method for content based image retrieval based on support vector machine classifier. In this method the feature extraction was done based on the colour string coding and string comparison. We succeed in transferring the images retrieval problem to strings comparison. Thus the computational complexity is decreases obviously. The image database used in our experiment contains 1800 colour images from Corel photo galleries. This CBIR approach has significantly increased the accuracy in obtaining results for image retrieval. © 2015 The Authors. Published by Elsevier B.V. Peer-review under responsibility of scientific committee of 2nd International Symposium on Big Data and Cloud Computing (ISBCC'15).

show abstract