Neural network-based face detection

Rowley, Henry A.; Baluja, Shumeet; Kanade, Takeo

doi:10.1109/cvpr.1996.517075

Cited by 800 publications

(1,036 citation statements)

References 4 publications

Supporting

Mentioning

1,004

Contrasting

Unclassified

Order By: Relevance

“…One of these is the artificial neural network (ANN), a mathematical model inspired by the structure and behavior of animal neurons (8)(9)(10). It consists of interconnected layers of artificial neurons and has been successfully used to address a variety of scientific problems, from face recognition (11), protein phosphorylation site prediction (12), tumor diagnosis (13) to the classification of bacterial morphotypes (14). ANN analysis has also found application in industrial quality control, such as in machine vision based grading of apples (15) or cherries (16).…”

Section: Original Articlementioning

confidence: 99%

Automated quality assessment of autonomously acquired microscopic images of fluorescently stained bacteria

Zeder

Kohler

2009

Cytometry Pt A

View full text Add to dashboard Cite

Quality assessment of autonomously acquired microscopic images is an important issue in high-throughput imaging systems. For example, the presence of low quality images (!10%) in a dataset significantly influences the counting precision of fluorescently stained bacterial cells. We present an approach based on an artificial neural network (ANN) to assess the quality of such images. Spatially invariant estimators were extracted as ANN input data from subdivided images by low level image processing. Different ANN designs were compared and [400 ANNs were trained and tested on a set of 25,000 manually classified images. The optimal ANN featured a correct identification rate of 94% (3% false positives, 3% false negatives) and could process about 10 images per second. We compared its performance with the image quality assessment by different humans and discuss the difficulties in assigning images to the correct quality class. The computer program and the documented source code (VB

show abstract

Section: Original Articlementioning

confidence: 99%

Automated quality assessment of autonomously acquired microscopic images of fluorescently stained bacteria

Zeder

Kohler

2009

Cytometry Pt A

View full text Add to dashboard Cite

show abstract

“…The remaining plots show how such neurons respond to test images. The top row shows four schematic patterns and two photographic stimuli (Rowley et al 1998). Below each is the LGN response to that image (second row), the FSA response after prenatal training on three-dot patterns (third row), and the FSA response after postnatal training on real faces (bottom row).…”

Section: Face Preference Experimentsmentioning

confidence: 99%

Constructing visual function through prenatal and postnatal learning

Miikkulainen¹

2007

Neuroconstructivism Volume TwoPerspectives and Prospects

View full text Add to dashboard Cite

Although environment-driven learning can explain much of postnatal neural development, substantial organization and functional ability is present even at birth. Recent experimental discoveries of widespread spontaneous neural activity suggest that prenatal development may utilize very similar mechanisms and principles as postnatal learning, driven by internally generated sources instead of the environment. This chapter shows how this idea can explain features of the organization and function of the primary visual cortex (V1) and higher level face-processing areas. Specifically, we simulate how neural preferences for contour orientation and human faces can develop prenatally from internally generated activity and postnatally from natural image stimuli. These simulations are based on HLISSOM, a hierarchical self-organizing model of the development of topographic neural maps. The results match experimental neuroimaging and psychophysical data from newborn and older animals and humans, and provide concrete predictions about infant behavior and neural activity for future experiments. They also suggest that combining internally generated activity with a learning algorithm is an efficient way to develop complex neural machinery.

show abstract

“…Group images containing faces with variation in pose, having moustache, structural components and slight variation in expressions and non-faces were used for testing. Rowley et al [13] have used around thousand images for training, where as in the proposed method, as facial wavelet-edge features are already extracted, the small training set is sufficient. This approach also detects faces with variation in pose and structural components.…”

Section: A Training Phasementioning

confidence: 99%

Face Detection in Skin-Toned Images Through Wavelet Edges and Neural Network

Lakshmi¹,

Kulkarni²

2012

IJCEE

View full text Add to dashboard Cite

Abstract-In this paper, an improved algorithm to detect faces in images with skin tone regions is proposed. Among the segmented candidate regions, facial edges detected using Canny and Sobel operators on wavelet approximation are suggested as feature set. These features are further classified using a neural-net proposed. Results of the test using the proposed algorithm are compared with those of the previous ones.

show abstract

Neural network-based face detection

Cited by 800 publications

References 4 publications

Automated quality assessment of autonomously acquired microscopic images of fluorescently stained bacteria

Automated quality assessment of autonomously acquired microscopic images of fluorescently stained bacteria

Constructing visual function through prenatal and postnatal learning

Face Detection in Skin-Toned Images Through Wavelet Edges and Neural Network

Contact Info

Product

Resources

About