A hierarchical learning network for face detection with in-plane rotation

Tivive, Fok Hing Chi; Bouzerdoum, A.

doi:10.1016/j.neucom.2008.04.036

Cited by 9 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the input window is chosen as the minimum window size that achieves good classification performance. Previous studies on visual pattern recognition problems showed that the HICA achieves good classification performance when using convolution masks of size 5 × 5 for each adaptive filter in Stage 2 [28,29]. Thus, the size of the convolution masks P j and Q j is set to 5 × 5 in all experiments, and the exponential and hyperbolic tangent activation functions are chosen for f and g, respectively.…”

Section: Experimental Methods and Resultsmentioning

confidence: 99%

A Human Gait Classification Method Based on Radar Doppler Spectrograms

Tivive

Bouzerdoum

Amin

2010

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

An image classification technique, which has recently been introduced for visual pattern recognition, is successfully applied for human gait classification based on radar Doppler signatures depicted in the time-frequency domain. The proposed method has three processing stages. The first two stages are designed to extract Doppler features that can effectively characterize human motion based on the nature of arm swings, and the third stage performs classification. Three types of arm motion are considered: free-arm swings, one-arm confined swings, and no-arm swings. The last two arm motions can be indicative of a human carrying objects or a person in stressed situations. The paper discusses the different steps of the proposed method for extracting distinctive Doppler features and demonstrates their contributions to the final and desirable classification rates.

show abstract

Section: Experimental Methods and Resultsmentioning

confidence: 99%

A Human Gait Classification Method Based on Radar Doppler Spectrograms

Tivive

Bouzerdoum

Amin

2010

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The cutoff ratio of the intersected areas to the joined areas of the two regions is set to 0.5 in our case. We compare the proposed method with the following detection methods: (1) ACF-multiscale [56], (2) HeadHunter [57], (3) CBSR [58], (4) Boosted Exemplar [59], (5) SURF frontal/multiview [60], (6) SURF Gentle-Boost [60], (7) Face++ [61], (8) PEP-Adapt [62], (9) Viola-Jones [63] and (10) the image-based method [27]. We select these methods since most of these methods are the state-of-the-art face detection methods based on hand-crafted features, and their results have been reported in the FDDB website [53].…”

Section: The Performance Comparison For Face Detectionmentioning

confidence: 99%

“…Deep learning models have demonstrated impressive performance for different computer vision applications [6,7,8,9,10,11,12]. The deep convolutional neural network (CNN) [13] can map raw data from a manifold to the Euclidean space, in which features may be linearly separable.…”

Section: Introductionmentioning

confidence: 99%

A fast face detection method via convolutional neural network

et al. 2020

View full text Add to dashboard Cite

Current face or object detection methods via convolutional neural network (such as OverFeat, R-CNN and DenseNet) explicitly extract multi-scale features based on an image pyramid. However, such a strategy increases the computational burden for face detection. In this paper, we propose a fast face detection method based on discriminative complete features (DCFs) extracted by an elaborately designed convolutional neural network, where face detection is directly performed on the complete feature maps. DCFs have shown the ability of scale invariance, which is beneficial for face detection with high speed and promising performance. Therefore, extracting multi-scale features on an image pyramid employed in the conventional methods is not required in the proposed method, which can greatly improve its efficiency for face detection. Experimental results on several popular face detection datasets show the efficiency and the effectiveness of the proposed method for face detection.

show abstract

“…This CNN architecture was very attractive to re-searchers at that time. Since then, many modified CNNs have been proposed for a variety of applications, such as face detection and recognition [3], [4], Chinese license plate recognition [5], and micro nucleus in human lympho-cyte image detection [6]. However, these modified architectures worked well with small-scale images.…”

Section: Introductionmentioning

confidence: 99%

A Robust-Texture Convolutional Neural Network

Nunsong

Woraratpanya

2019

MJCS

View full text Add to dashboard Cite

AlexNet was a breakthrough for the convolutional neural network (CNN) and showed the greatest successful mod- ified CNN that works well with large-scale images. However, it was unsuccessful in texture classification tasks. To extend CNN’s capability, this paper proposes a modified CNN architecture called a robust-texture convolutional neural network (RT-CNN) to serve both complex shape and texture classification tasks, especially in the following challenges: (i) the same class of images naturally contains various viewpoints, scales, uneven illuminations, etc. (ii) similarly shaped objects with different textures of images are often assigned into different classes; and (iii) dif- ferent shaped objects with similar textures of images are often assigned into the same class. The proposed scheme embeded a texture-embedded supplementary method, composed of texture compensation and supplement, into the CNN architecture. The texture compensation is constructed from texture subbands decomposed by 2D Littlewood-Paley empirical wavelet transform (2D Littlewood-Paley EWT). Then the texture supplement is constructed from texture subbands by using Gabor wavelet to extract multi-scale and multi-orientation texture features. Based on two challenging datasets, the experimental results show that RT-CNN outperforms all test baseline methods: AlexNet, T-CNN, and wavelet-CNN, in terms of recognition accuracy rate. On a typical dataset, the recognition accuracy rate of the proposed method is still better than those of T-CNN and wavelet-CNN, and is comparable to that of AlexNet.

show abstract

A hierarchical learning network for face detection with in-plane rotation

Cited by 9 publications

References 44 publications

A Human Gait Classification Method Based on Radar Doppler Spectrograms

A Human Gait Classification Method Based on Radar Doppler Spectrograms

A fast face detection method via convolutional neural network

A Robust-Texture Convolutional Neural Network

Contact Info

Product

Resources

About