COSFIRE: A Brain-Inspired Approach to Visual Pattern Recognition

Azzopardi, George; Petkov, Nicolai

doi:10.1007/978-3-319-12084-3_7

Cited by 4 publications

(3 citation statements)

References 53 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where γ represents the weight 6 that is applied to the values in the feature vector according to the spatial pyramid level they are coming from, making use of spatial information encoded within the descriptor.…”

Section: Stacked Classificationmentioning

confidence: 99%

“…In this work, we propose a fusion technique of features constructed from the output of a Convolutional Neural Network (CNN) and that of Combination of Shifted Filter Responses (COSFIRE) for age classification from face images. Both CNN and COSFIRE [6] approaches are trainable in that they learn feature detectors from training data. In particular, we use the VGG-Face pretrained CNN [32,37] and for COSFIRE we configure a new set of feature detectors.…”

Section: Introductionmentioning

confidence: 99%

“…SVM scripts imported from LiBSVM library[13] 6. γ = 1 for level-2 pyramid responses, γ = 0.5 for level-1 pyramid responses and γ = 0.25 for level-0 pyramid responses 7.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Age group recognition from face images using a fusion of CNN- and COSFIRE-based features

Demajo

Guillaumier

Azzopardi

2019

Proceedings of the 2nd International Conference on Applications of Intelligent Systems

View full text Add to dashboard Cite

Automatic age group classification is the ability of an algorithm to classify face images into predetermined age groups. It is an important task due to its numerous applications such as monitoring, biometrics and commercial profiling. In this work we propose a fusion technique that combines CNN-and COSFIRE-based features for the recognition of age groups from face images. Both CNN and COSFIRE are trainable approaches that have been demonstrated to be effective in various computer vision applications. As to CNN, we use the pre-trained VGG-Face architecture and for COSFIRE we configure new COSFIRE filters from training data. Since recent literature suggests that CNNs deliver the highest accuracy rates within such problems, the hypothesis which we want to investigate in this work is whether combining CNN and COSFIRE approaches together will improve results. The proposed fusion technique using stacked Support Vector Machine (SVM) classifiers, and trained and tested with the FERET data set images has shown that, indeed, CNN-and COSFIRE-based features are complimentary as their combination reduces the error rate by more than 25%.

show abstract

Section: Stacked Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%