An Edge Clustered Segmentation Based Model for Precise Image Retrieval

Devareddi, Ravi Babu; A., Srikrishna

doi:10.21817/indjcse/2022/v13i3/221303094

Cited by 4 publications

(2 citation statements)

References 19 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the proposed research, query image and dataset image features are extracted by using regrouping class-prior estimation (RECPE) algorithm [27] with support of the OPDED approach [38] and the interlinked feature query (IFQ) method is used to interlink features of an image. Thus, elements are trained to the ensemble model.…”

Section: Methodsmentioning

confidence: 99%

Query-based image tagging model using ensemble learning with enhanced artificial bee colony optimization

Devareddi

Srikrishna²

2023

IJEECS

View full text Add to dashboard Cite

Digital images make up most multimedia data and are analysed in computer vision applications. Daily uploads of millions of pictures to Internet archives such as satellite image repositories complicate multimedia content and image graphs. As feature vectors, content based image retrieval (CBIR) and image classification models represent high-level image viewpoints. Observing photos recognizes objects and evaluates their significance for image enhancement. To access the visual information of big datasets, efficiently retrieve and query picture graphs. The artificial bee colony (ABC) algorithm is inspired by the foraging behaviour of honeybee swarms. ABC is susceptible to laziness in convergence and local optimums, just like other optimization methods. This study created an enhanced ABC (EABC) model to enhance precision. This study presents query-based image tagging model using ensemble learning with EABC (QbITM-ELEABC) for CBIR for appropriately tagging images based on the query image. We examine a number of convolutional neural network (CNNs) with varying topologies that can be trained on the dataset with varying degrees of similarity. As representations, each network extracts class probability vectors from images. The final image representation is created by combining the ensemble's class probability vectors with image.

show abstract

Section: Methodsmentioning

confidence: 99%

Query-based image tagging model using ensemble learning with enhanced artificial bee colony optimization

Devareddi

Srikrishna²

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…In the proposed research, the images from the image dataset are initially considered, image processing techniques are applied to the idea, and all the features are extracted using an edge clustered segmentation model [Devareddi et al (2022)]. Weight allocation is done on the highly correlated features.…”

Section: Methodsmentioning

confidence: 99%

Interlinked Feature Querybased Image Retrieval Model for Content-Based Image Retrieval

Devareddi¹,

A.²

2022

INDJCSE

View full text Add to dashboard Cite

Visual data retrieval and management have become significant research areas due to the rapid expansion of image data on the internet and the rise of multimedia technologies. Many professional organizations, such as journalists, engineers, agriculture, urban planning to meteorology and art historians, have a shared requirement to discover a particular image in an extensive collection. Researchers were inspired by their difficulties with text-based picture retrieval to create new ways to encode visual index input. Researchers are focused on Content-Based Image Retrieval (CBIR) to overcome these issues and improve the performance of image retrieval models. Using the optical characteristics of an image, such as colour, body, and texture, CBIR searches massive databases for user-requested photos with a query image. An image's visual features are extracted using CBIR's feature extraction method, which is done automatically, without human intervention. The extraction of crucial points in a picture is done using the feature extraction algorithm in this research. It is possible to think of a CBIR system's design as a group of modules that work together to get database images in response to a specific query. This research proposes an Interlinked Feature Query-based Image Retrieval Model (IFQ-IRM) for accurate image extraction from the image database. Image queries are transformed into feature vectors by the system. The extracted features of the query instance and the photos in the databases are then compared, and an indexing strategy is used to retrieve the images. The proposed model results show that image extraction accuracy is better than traditional models.

show abstract