A Survey On: Content Based Image Retrieval Systems Using Clustering Techniques For Large Data sets

Jain, Monika; Singh, Sanjay Kumar

doi:10.5121/ijmit.2011.3403

Cited by 20 publications

(2 citation statements)

References 81 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Digital image classification procedures are differentiated as being either supervised or unsupervised (clustering). [13] Supervised Classification: In supervised category objects/pixels belonging to a notable class are used for "training" of the system and drawing decision lines between completely different categories. New objects/pixels are known based on the choice lines.…”

Section: Local Binary Patternmentioning

confidence: 99%

Content Based Image Retrival Using Different Clustering Techniques

2023

IJSREM

View full text Add to dashboard Cite

CBIR (Content based image retrieval) is the software system for retrieving the images from the database by using their features. In CBIR technique, the images are retrieved from the dataset by using the features like color, text, shape,texture and similarity. Object recognition technique is used in CBIR. Research on multimedia systems and content-based image retrieval is given tremendous importance during the last decade. The reason behind this is the fact that multimedia databases handle text, audio, video and image information, which are of prime interest in web and other high end user applications. Content-based Image retrieval deals with the extraction of knowledge, image data relationship, or other patternsnot expressly keep within the pictures. It uses ways from computer vision, image processing, image retrieval, data retrieval, machine learning, database and artificial intelligence. Rule retrieval has been applied to large image databases. The proposedsystem gives average accuracy of 90%. Keywords— CBIR, Color feature, Shape feature, Texture feature, Feature extraction, Clustering, Image Retrieval.

show abstract

Section: Local Binary Patternmentioning

confidence: 99%

Content Based Image Retrival Using Different Clustering Techniques

2023

IJSREM

View full text Add to dashboard Cite

show abstract

“…Image recovery is an important part of image retrieval or content based image retrieval (CBIR) technology. Some CBIR approaches that have been taken include semantic [4], [5], relevance feedback [6], [7], machine learning or algorithmic approaches [8]- [11], hierarchical categories [12] and, multimodal queries (image retrieval with various types of queries) [13]. The task of detecting the number of objects contained in an image can be utilized in a variety of life applications, including detecting the number of objects in the fetal ultrasound image, detecting the number of vehicles passing a crossroads, counting the number of visitors in a shopping center as a recommendation for building repairs, counting the number of passengers in a fleet, count the number of audiences, count the number of oil palm bunches in each cubic truck and many other types of applications [14].…”

Section: Introductionmentioning

confidence: 99%

Extraction of object image features with gradation contour

et al. 2021

View full text Add to dashboard Cite

Image retrieval using features has been used in previous studies including shape, color, texture, but these features are lagging. With the selection of high-level features with contours, this research is done with the hypothesis that images on objects can also be subjected to representations that are commonly used in natural images. Considering the above matters, we need to research the feature extraction of object images using gradation contour. From the results of the gradation contour test results, there is linearity between the results of accuracy with the large number of images tested. Therefore, it can be said that the influence of the number of images will affect the accuracy of classification. The use of contour gradation can be accepted and treated equally in all image types, so there is no more differentiation between image features. The complexity of the image does not affect the method of extracting features that are only used uniquely by an image. From the results of testing the polynomial coefficient savings data as a result of the gradation contour, the highest result is 81.40% with the highest number of categories and the number of images tested in the category is also higher.

show abstract