Local Oriented Statistics Information Booster (LOSIB) for Texture Classification

García-Olalla, Oscar; Alegre, Enrique; Fernández-Robles, Laura; González-Castro, V́ıctor

doi:10.1109/icpr.2014.201

Cited by 22 publications

(17 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, LOSIB [47] is a descriptor enhancer based on LBP that computes local oriented statistical information in the whole image. We have adapted it to face analysis concatenating the histograms obtained from a grid of cells.…”

Section: Local Binary Patterns (Lbp)mentioning

confidence: 99%

Descriptors and regions of interest fusion for in- and cross-database gender classification in the wild

Castrilln-Santana

Lorenzo-Navarro

Ramn-Balmaseda

2017

Image and Vision Computing

View full text Add to dashboard Cite

Gender classification (GC) has achieved high accuracy in different experimental evaluations based mostly on inner facial details. However, these results do not generalize well in unrestricted datasets and particularly in cross-database experiments, where the performance drops drastically. In this paper, we analyze the state-of-the-art GC accuracy on three large datasets: MORPH, LFW and GROUPS. We discuss their respective difficulties and bias, concluding that the most challenging and wildest complexity is present in GROUPS. This dataset covers hard conditions such as low resolution imagery and cluttered background. Firstly, we analyze in depth the performance of different descriptors extracted from the face and its local context on this dataset. Selecting the bests and studying their most suitable combination allows us to design a solution that beats any previously published results for GROUPS with the Dago's protocol, reaching an accuracy over 94.2%, reducing the gap with other simpler datasets. The chosen solution based on local descriptors is later evaluated in a cross-database scenario with the three mentioned datasets, and full dataset 5-fold cross validation. The achieved results are compared with a Convolutional Neural Network approach, achieving rather similar marks. Finally, a solution is proposed combining both focuses, exhibiting great complementarity, boosting GC performance to beat previously published results in GC both cross-database, and full in-database evaluations.

show abstract

Section: Local Binary Patterns (Lbp)mentioning

confidence: 99%

Descriptors and regions of interest fusion for in- and cross-database gender classification in the wild

Castrilln-Santana

Lorenzo-Navarro

Ramn-Balmaseda

2017

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…This is done computing the difference of each neighborhood pixel with the neighborhood mean, µ, instead of the central pixel gray value. -Local Oriented Statistics Information Booster (LOSIB) [21]. Texture enhancer based on LBP, that computes the local oriented statistical information in the whole cell.…”

Section: Descriptorsmentioning

confidence: 99%

Multi-scale score level fusion of local descriptors for gender classification in the wild

Castrillón-Santana

Lorenzo-Navarro

Ramón-Balmaseda

2016

Multimed Tools Appl

View full text Add to dashboard Cite

The 2015 FRVT gender classification (GC) report evidences the problems that current approaches tackle in situations with large variations in pose, illumination, background and facial expression. The report suggests that both commercial and research solutions are hardly able to reach an accuracy over 90% for The Images of Groups dataset, a proven scenario exhibiting unrestricted or in the wild conditions. In this paper, we focus on this challenging dataset, stepping forward in GC performance by observing: 1) recent literature results combining multiple local descriptors, and 2) the psychophysics evidences of the greater importance of the ocular and mouth areas to solve this task. We therefore make use of holistic and inner facial patches to extract features, that are later combined via a score level fusion strategy. The achieved results support the main information provided by the ocular and the mouth areas. Indeed, the combination of multiscale extracted features increases the overall accuracy to over 94%, reducing notoriously the classification error if compared with tuned holistic and deep learning approaches.

show abstract

“…LOSIB, described recently by [19], is a descriptor enhancer. It is based on LBP, but the main difference is that it computes the local oriented statistical information in the whole image.…”

Section: Local Oriented Statistics Information Boostermentioning

confidence: 99%

On using periocular biometric for gender classification in the wild

Castrillón-Santana

Lorenzo-Navarro

Ramón-Balmaseda

2016

Pattern Recognition Letters

View full text Add to dashboard Cite

Local Oriented Statistics Information Booster (LOSIB) for Texture Classification

Cited by 22 publications

References 20 publications

Descriptors and regions of interest fusion for in- and cross-database gender classification in the wild

Descriptors and regions of interest fusion for in- and cross-database gender classification in the wild

Multi-scale score level fusion of local descriptors for gender classification in the wild

On using periocular biometric for gender classification in the wild

Contact Info

Product

Resources

About