Multichannel Decoded Local Binary Patterns for Content-Based Image Retrieval

Dubey, Shiv Ram; Singh, Satish Kumar; Singh, Rajat Kumar

doi:10.1109/tip.2016.2577887

Cited by 166 publications

(97 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The top n number of faces is retrieved based on the lower distances, computed using the distance measures. The Chi-square distance measure is generally used in the experiments in this paper, whereas other distances like Euclidean, Cosine, L1, and D1 are also tested with the proposed descriptor to find its suitability [44], [20].…”

Section: Distances Measuresmentioning

confidence: 99%

Local directional relation pattern for unconstrained and robust face retrieval

Dubey

2019

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Face recognition is still a very demanding area of research. This problem becomes more challenging in unconstrained environment and in the presence of several variations like pose, illumination, expression, etc. Local descriptors are widely used for this task. The most of the existing local descriptors consider only few immediate local neighbors and not able to utilize the wider local information to make the descriptor more discriminative. The wider local information based descriptors mainly suffer due to the increased dimensionality. In this paper, this problem is solved by encoding the relationship among directional neighbors in an efficient manner. The relationship between the center pixel and the encoded directional neighbors is utilized further to form the proposed local directional relation pattern (LDRP). The descriptor is inherently uniform illumination invariant. The multi-scale mechanism is also adapted to further boost the discriminative ability of the descriptor. The proposed descriptor is evaluated under the image retrieval framework over face databases. Very challenging databases like PaSC, LFW, PubFig, ESSEX, FERET, AT&T, and FaceScrub are used to test the discriminative ability and robustness of LDRP descriptor. Results are also compared with the recent state-of-the-art face descriptors such as LBP, LTP, LDP, LDN, LVP, DCP, LDGP and LGHP. Very promising performance is observed using the proposed descriptor over very appealing face databases as compared to the existing face descriptors. The proposed LDRP descriptor also outperforms the pretrained ImageNet CNN models over large-scale FaceScrub face dataset. Moreover, it also outperforms the deep learning based DLib face descriptor in many scenarios.Unconstrained and robust face recognition is the current demand for the betterment of the quality life. Most of the early days research has been conducted in a very controlled environment, where users have given their facial images in frontal pose, under consistent lighting, without glasses or occlusion, etc. Some researchers also tried to develop the face recognition approaches robust for specific geometric and photometric changes such as pose, illumination, motion blur, etc. [68], [14], [29], [15], [50]. The face recognition approaches are surveyed time to time by many researchers [75], [74], [13]. The face recognition approaches are categorized into three major areas, namely deep learning based face recognition [58], [62], traditional learning based face recognition [6], [67], [33], [41], [40], and hand-crafted feature based face recognition [71], [22], [7]. The deep learning based approaches are being popular due to high performance, but at the cost of increased complexity in terms of the time, computing power and data size. The deep learning based approaches are also biased towards the training data. The main drawback of the traditional learning based descriptors are the dependency over the training database and vocabulary size. The hand-designed local descriptors are very simple from design aspect. ...

show abstract

Section: Distances Measuresmentioning

confidence: 99%

Local directional relation pattern for unconstrained and robust face retrieval

Dubey

2019

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to show the superiority of the proposed technique, the results are also compared with those of Dubey et al [45], Xiao et al [46], Zhou et al [47], Shrivastava et al [48], Kundu et al [49], Zeng et al [50], Walia et al [51], Ashraf et al [52] and ElAlami et al [53]. Table 2 presents the class-wise comparison of the proposed system with comparative systems in terms of average precision values.…”

Section: Precision and Recall Evaluationmentioning

confidence: 99%

An Ensemble Based Evolutionary Approach to the Class Imbalance Problem with Applications in CBIR

et al. 2018

View full text Add to dashboard Cite

Abstract:In order to lower the dependence on textual annotations for image searches, the content based image retrieval (CBIR) has become a popular topic in computer vision. A wide range of CBIR applications consider classification techniques, such as artificial neural networks (ANN), support vector machines (SVM), etc. to understand the query image content to retrieve relevant output. However, in multi-class search environments, the retrieval results are far from optimal due to overlapping semantics amongst subjects of various classes. The classification through multiple classifiers generate better results, but as the number of negative examples increases due to highly correlated semantic classes, classification bias occurs towards the negative class, hence, the combination of the classifiers become even more unstable particularly in one-against-all classification scenarios. In order to resolve this issue, a genetic algorithm (GA) based classifier comity learning (GCCL) method is presented in this paper to generate stable classifiers by combining ANN with SVMs through asymmetric and symmetric bagging. The proposed approach resolves the classification disagreement amongst different classifiers and also resolves the class imbalance problem in CBIR. Once the stable classifiers are generated, the query image is presented to the trained model to understand the underlying semantic content of the query image for association with the precise semantic class. Afterwards, the feature similarity is computed within the obtained class to generate the semantic response of the system. The experiments reveal that the proposed method outperforms various state-of-the-art methods and significantly improves the image retrieval performance.

show abstract

“…The experiments were conducted using Matlab software; the results indicated that region based and color histogram based methods are effective methods. Dubey et al [8] introduced two multi-channel decoded local binary patterns; the experiments applied on 10 DB with variety natural scene and textures. PyykkÖ and Glowacka [9] used deep neural network for interactive content based image retrieval by using few training samples to learn automatically from users' interaction and feedback to reduce the training time.…”

Section: Literature Reviewmentioning

confidence: 99%

An Online Content Based Email Attachments Retrieval System

Jameel

Mohammed

George

2017

KJAR

View full text Add to dashboard Cite

E-mail is one of the most popular programs used by most people today. As a result of the continuous daily use, thousands of messages are accumulated in the electronic box of most individuals, which make it difficult for them after a period of time to retrieve the attachments of these messages. Most Email providers constantly improved their search technology, but till now there is something could not be done; i.e., searching inside attachments. Some email providers like Gmail has added searching words inside attachments for some file types (.pdf files, .doc documents, .ppt presentations) but for image files this feature not supported till now. However, E-mail providers and even modern researches have not focused on retrieving the image attachments in the Email box. The paper was aimed to introduce a novel idea of using Content based Image Retrieval (CBIR) in E-mail application to retrieve images from email attachments based on entire contents. The work main phases are: feature extraction based on color features and connect to Email server to read Emails, the second phase is retrieving similar image attachments. The tests carried on mail inbox contain 100 messages with 500 image attachments and gave good precision and recall rates When the threshold value is less than or equal to 0.4.

show abstract

Multichannel Decoded Local Binary Patterns for Content-Based Image Retrieval

Cited by 166 publications

References 51 publications

Local directional relation pattern for unconstrained and robust face retrieval

Local directional relation pattern for unconstrained and robust face retrieval

An Ensemble Based Evolutionary Approach to the Class Imbalance Problem with Applications in CBIR

An Online Content Based Email Attachments Retrieval System

Contact Info

Product

Resources

About