Robust face analysis using convolutional neural networks

Fasel, Beat

doi:10.1109/icpr.2002.1048231

Cited by 77 publications

(45 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The combination of many features increases the detector efficiency, (Wu & Nevatia, 2008) combined HOG, edgelet and covariance features. The multilayer network is widely used in pattern recognition, such as face detection (Garcia & Delakis, 2004), handwritten digit recognition (LeCun, Bottou, Bengio, & Haffner, 1998), facial expression analysis (Fasel, 2002). Hubel and Wiesel (1965) introduced Neural Network ideas, where local features are extracted following certain hierarchical structure.…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Detection Based on Multi-Block Local Binary Pattern and Biologically Inspired Feature

Halidou¹,

You²,

Bogno³

2014

CIS

View full text Add to dashboard Cite

Nowadays pedestrian detection plays an important role in security and driving assistance. Detecting moving object is complex, and some of the detection methods are comparatively ineffective and slow. In relation to human detection it is very useful to combine independent information sources, such as appearance and motion. To achieve acceptable detection performance, we propose inter-frames differencing image to compute the region of interest, and MB-BIF to extract features. The MB-BIF approach combines two well-known methods, the Multi-Block Local Binary Pattern and Biologically Inspired Method. We evaluate the performance of different features descriptors on different databases, and our method shows good efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

Pedestrian Detection Based on Multi-Block Local Binary Pattern and Biologically Inspired Feature

Halidou¹,

You²,

Bogno³

2014

CIS

View full text Add to dashboard Cite

show abstract

“…Convolutional neural networks are powerful hierarchical multilayered networks designed for visual pattern recognition problems, such as face detection [7], handwritten digit recognition [8], facial expression analysis [9], and video quality assessment [10], just to name a few. These neural networks are inspired by Hubel and Wiesel hierarchy model of the visual cortex [11], where the processing elements are structured in a hierarchical order to extract local features from the input image.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…In LeNet-5 and its predecessors [7], [9], the processing elements employed in the network are sigmoid-type neurons, where the neuron performs a weighted sum of the input signals, which is added to a bias term before passing through a nonlinear activation function to generate a neural response. The Neocognitron, on the other hand, has three types of processing elements, including the V-cell that enables the network to be invariant to distortions and translations.…”

Section: Proposed Pedestrian Detection System a Network Architecmentioning

confidence: 99%

A biologically inspired visual pedestrian detection system

Tivive

Bouzerdoum

2008

2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)

View full text Add to dashboard Cite

In this paper, we present a biologically inspired method for detecting pedestrians in images. The method is based on a convolutional neural network architecture, which combines feature extraction and classification. The proposed network architecture is much simpler and easier to train than earlier versions. It differs from its predecessors in that the first processing layer consists of a set of pre-defined nonlinear derivative filters for computing gradient information. The subsequent processing layer has trainable shunting inhibitory feature detectors, which are used as inputs to a pattern classifier. The proposed pedestrian detection system is evaluated on the DaimlerChrysler pedestrian classification benchmark database and its performance is compared to the performance of support vector machines and Adaboost classifiers. A Biologically Inspired Visual Pedestrian Detection SystemFok Hing Chi Tivive, Member, IEEE, and Abdesselam Bouzerdoum, Senior Member, IEEE Abstract-In this paper, we present a biologically inspired method for detecting pedestrians in images. The method is based on a convolutional neural network architecture, which combines feature extraction and classification. The proposed network architecture is much simpler and easier to train than earlier versions. It differs from its predecessors in that the first processing layer consists of a set of pre-defined nonlinear derivative filters for computing gradient information. The subsequent processing layer has trainable shunting inhibitory feature detectors, which are used as inputs to a pattern classifier. The proposed pedestrian detection system is evaluated on the DaimlerChrysler pedestrian classification benchmark database and its performance is compared to the performance of support vector machines and Adaboost classifiers.

show abstract

“…This advantage is significant in the field of image processing, since without the use of appropriate constraints, the high dimensionality of the input data generally leads to ill-posed problems. To some extent, CNNs reflect models of biological vision systems [8]. CNNs take raw data, without the need for an initial separate pre-processing or feature extraction stage: in a CNN the feature extraction and classification stages occur naturally within a single framework.…”

Section: Introductionmentioning

confidence: 99%

“…CNNs have been shown to be ideally suited for implementation in hardware, enabling very fast real-time implementation [9]. Although CNN have not been widely applied in image processing, they have been applied to handwritten character recognition [2,[9][10][11] and face recognition [7,8,12]. CNNs may be conceptualized as a system of connected feature detectors with non-linear activations.…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Networks for Image Processing: An Application in Robot Vision

Browne¹,

Ghidary²

2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) represent an interesting method for adaptive image processing, and form a link between general feedforward neural networks and adaptive filters. Two dimensional CNNs are formed by one or more layers of two dimensional filters, with possible non-linear activation functions and/or down-sampling. Conventional neural network error minimization methods may be used to optimize convolutional networks in order to implement quite powerful image transformations. CNNs possess key properties of translation invariance and spatially local connections (receptive fields). CNNs are an interesting alternative when the the input is spatially or temporally distributed, and the desired output of a system may be specified. The present paper presents a description of the convolutional network architecture, and an application to a practical image processing application on a mobile robot. As a formal CNN framework has not yet been specified in the literature, we describe CNNs in some detail, conceptually and formally. A CNN is used to detect and characterize cracks on an autonomous sewer inspection robot. Although cracks are relatively easy to detect by a human operator, autonomous sewer inspection necessitates the detection of pipe damage using computer vision methods. This is an appropriate application for trainable data-based computer vision methods, since prior specification of appropriate of the filtering / detection method is quite difficult. The The CNN architecture used involved a total of five layers: a single input and output map, and three hidden layers. The filter sizes used in all cases were 5x5, and the common activation function used was a log-sigmoid. The number

show abstract

Robust face analysis using convolutional neural networks

Cited by 77 publications

References 8 publications

Pedestrian Detection Based on Multi-Block Local Binary Pattern and Biologically Inspired Feature

Pedestrian Detection Based on Multi-Block Local Binary Pattern and Biologically Inspired Feature

A biologically inspired visual pedestrian detection system

Convolutional Neural Networks for Image Processing: An Application in Robot Vision

Contact Info

Product

Resources

About