Content based image retrieval system using clustered scale invariant feature transforms

Montazer, Gholam Ali; Giveki, Davar

doi:10.1016/j.ijleo.2015.05.002

Cited by 51 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Montazer et al [13] they use SIFT for pictures properties, and then apply k-means clustering. They use dimension reductions to make properties extra effective.…”

Section: Related Workmentioning

confidence: 99%

CBIR System Using Scaled Conjugate Gradient Feed-Forward Neural Network

2020

IJATCSE

View full text Add to dashboard Cite

Images produced by copious of application has now become the centre of attraction for researchers. The task of retrieval of desired image from the ocean of images is quite tedious task. The paper focuses on mining of database from the picture descriptions that are recovered from the same picture known as Content Based Image Retrieval (CBIR). In this paper, we have used colour, texture and shape picture description and Scaled Conjugate Gradient feed-forward neural network (SCG-FFNN). Initially we have prepared the model using colour histogram for colour feature, wavelet moments for texture feature and edge-histogram and edgedirection for shape features; then trains the dataset using FFNN. The trained database is tested with a picture, and generates the like pictures from it. The execution of the system is calculated with the help of precision and recall parameter and the outcomes are found to be high as compare to other research effort. The practical work has been conducted with Corel and Caltech dataset.

show abstract

“…Montazer et al [13] they use SIFT for pictures properties, and then apply k-means clustering. They use dimension reductions to make properties extra effective.…”

Section: Related Workmentioning

confidence: 99%

CBIR System Using Scaled Conjugate Gradient Feed-Forward Neural Network

2020

IJATCSE

View full text Add to dashboard Cite

show abstract

“…To overcome the above drawbacks, integration of both spatial and temporal features has to be done. As stated to the newly hypothesized algorithm by acquiring the methods like HSV color histogram [15]and motion histogram [16]to extricate color and motion features. The spatial information acquires the color features and temporal information acquires the motion feature.…”

Section: Introductionmentioning

confidence: 99%

A Scheme for Shot Detection and Video Retreival using Spatio Temporal Features

2019

IJRTE

View full text Add to dashboard Cite

There has been a revolution in multimedia with technological advancement. Hence, Video recording has increased in leaps and bounds. Video retrieval from a huge database is cumbersome by the existing text based search since a lot of human effort is involved and the retrieval efficiency is meager as well. In view of the present challenges, video retrieval based on video content prevails over the existing conventional methods. Content implies real video information such as video features. The performance of the Content Based Video Retrieval (CBVR) depends on Feature extraction and similar features matching. Since the selection of features in the existing algorithms is not effective, the retrieval processing time is more and the efficiency is less. Combined features of color and motion have been proposed for feature extraction and Spatio-Temporal Scale Invariant Feature Transform is used for Shot Boundary Detection. Since the characteristic of color feature is visual video content and that of motion feature is temporal content, these two features are significant in effective video retrieval. The performance of the CBVR system has been evaluated on the TRECVID dataset and the retrieved videos reveal the effectiveness of proposed algorithm.

show abstract

“…In [3], the authors reduced the number of SIFT features used for indoor scene representation based on the observation that a majority of the detected key points do not match between images that share common camera view point. Authors of [4] represented objects by clustering SIFT features of an object with k-means to solve content based image retrieval (CBIR) problem. Methods such as PCA-SIFT [5] and feature quantization [7] reduce feature dimensionality.…”

Section: Introductionmentioning

confidence: 99%

Feature Set Consolidation for Object Representation by Parts

Yadav¹,

Ladha²,

Deshpande³

et al. 2019

2019 IEEE International Symposium on Multimedia (ISM)

View full text Add to dashboard Cite

Image data is growing by leaps and bounds. Machine learning based applications that run on image datasets increasingly use local image feature descriptors. In a sense, we can now visualize images as objects with features as parts. Typically there are thousands of local features per image, resulting in an explosion of feature set size for already humungous image datasets. In this paper we present a feature set consolidation strategy based on two aspects: pruning of non-discriminatory features across different object types and association of matching features for the same object type. We showcase the effectiveness of our consolidation strategy by performing classification on a building dataset. Our method reduces storage space footprint (~5%) and classification runtime (~4%), and increases classification accuracy (~2%).

show abstract

Content based image retrieval system using clustered scale invariant feature transforms

Cited by 51 publications

References 10 publications

CBIR System Using Scaled Conjugate Gradient Feed-Forward Neural Network

CBIR System Using Scaled Conjugate Gradient Feed-Forward Neural Network

A Scheme for Shot Detection and Video Retreival using Spatio Temporal Features

Feature Set Consolidation for Object Representation by Parts

Contact Info

Product

Resources

About