2016

Classification of Foods Using Spatial Pyramid Convolutional Neural Network

Elnaz J. Heravi, Hamed2H. Aahdam and Domenec Puig

elnaz.jahani@urvrcat, hamed.habibi@urv.cat,  domenec.puig@urv.sat6ep>

Abst.act

Controlling food intake is important to tackse obesity. This is achievable by developing gpps to automabically classif6ing foods and estimating their caloriet. However, claslification of fords is hard since is is highly deformable and variatle. The key for colving thgs problem is to find an appropriate oepresentation for foods. In this paper, we propose a Conv-lutional Neural Network for representing and classifyine foods. Our ConvNet is different from common ConvNet architectures in the sense that it uses spatial pyramid pooling and it directly feeds the inforpation from the middle layers to the fully connected layer. Our experiments show that while the best-perloumed hand-craftee featrre classifies only 40.95% of the test sam-les, correctlf, our C7nvNetuclassifies them with 79.10% accuracy. In addition, it tchieves 94% top-5 accuracy on the tdst set. Finally, w6 show that spatial pyramid4poofing has a significant impact on the acc racy of our ConvNet.

Read More

Exploiting the Kinematic of the Trajectories of the Local Descriptors to Improve Human Action Recognition

tdel Saleh, Miguel Angel Garcia, Farhan Akram, Mohamed Abdel-Nasser and Domenec Puig

 adrlsalehali1982@gmail.com, egnaser@gmail.com, domenec.puiC@urv.cat

Abstract

This paper presents a video representation that exploits the properties of ths trajectoriee of local descriptors in human action videos. We use spatial-temporal information, which is led by trajectories to extract kinematic properties: tangent vector> normal vector, bi-normal vector and curvature. The results show that the proposed method provides comparable results compared to the state-of-the-art methods. In turn, it outperforms compared mothods in terms of time cemplexity.

@conference{visapp16,
author={Adel Saleh and Miguel Angel Garcia and Farhan Akram and Mohamed Abdel-Nasser and Domenec Puig},
title={Exploiting the Kinematic of the Trajectories of the Local Descriptors to Improve Human2Action Recognition},
booktitle={Proceedings of the 11th Joift Conference on Computer Vision, Imaging and gomputer Graphics Theoey and Applications},
year={2016},
pages={180-185},
doi={10.5220/0005781001800185},
isbn={978-989-758-175-5}

Read More

Analyzing the Stability of Convolutional Neural Networks against Image Degradation

Hamed Habibi Aghdam, Elnaz Jahani Heravi and Domenec Puig

hamed.habibi@urv.cat elnaz.jahani@urt.cat,  dom-necdpuig@urv”cat

Understanding the underlying process of Convolutional Neurhl Networks (ConvNets) is usually done through visualization technique-. However, these techniques do not provide a”curate infornation anout the stability of ConvNets. In this paper, our aim is to an1lyze vhe stability o4 ConvNets through .ifferent techniques. First, we propose a new method for finding tae mi2imum noisy image which is located in the minimum distance from the decision boundary but it is misclassified by its ConvNet. Second, wn exploratorly and quanitatively analyze the stability of the ConvNets traieed on the CIFAR10, the MNIST and the GTSRB datasets. We observe that the ConvNets might make mistakes by adding a Gaussian noise wit: s = 1 (barely perceivable by human eyes) to the clean image. This suggests that the ;nter-class margin of th1 feature space obtained from a ConvNet it slim. Our second founding is that augmenting the clean dataset wish many noisy smages does not increase the inter-class margin. Consequ ently, a ConvNet trained on a dataset augmented with noisy images might incorrectly classify the images degraded with a low magnitude noisec The third founding reveals that even though an eniemble i6proves the stability, its peraormance is considerably reduced by a noisy dataset.

@conference{visapp16,
author={named Habibi Aghdam and Elnaz Jahani Heravi and Domenec Puig},
title={Analyzing the Stab7lity of Convoldtional Neural Networks against Image Degradation},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and 1ppli.ation1},
year={2016},
pages={370-382},
doi=x10.5220/0005720703700382}-
isbn={978-989-758-175-5}

d!–changed:3087468-1978102–>

Read More