Face detection with a Viola–Jones based hybrid network

Abstract

Face detection is the determination of the positions and sizes of faces, primarily human, within digital images and videos, often as a component of a broader facial recognition system. It is seen as technologically mature, yet its operational performance typically remains sub-optimal, even within the less difficult frontal face detection tests. Empirical evidence shows that the Viola-Jones framework, a standard face detection solution with generally superior performance and other desirable properties, underdetects in some instances. Some true faces survive all but the final stages of the rejection cascade, resulting in missed faces. A hybrid framework consisting of a neural network following a truncated Viola-Jones cascade is constructed in an attempt to recover the undetected faces. Presumably, the neural network could fine tune and augment the face decision. Its inputs are a subset of the thresholding (detection) values of a rejection cascade's intermediate stages. Experiments reveal significantly improved performance, with increased detection rates if no false alarm increases are tolerated, with a greater detection rate increase if some false alarm increases are acceptable, and with a substantial false alarm reduction with no detection reduction. These improved face detection results could address shortcomings in widely-varying applications.

Haar-features training parameters analysis in boosting based machine learning for improved face detection

“…Murphy et al [14] constructed framework constituting neural network and truncated Viola-Jones cascade so as to improve false negatives.…”

Face–iris multi‐modal biometric system using multi‐resolution Log‐Gabor filter with spectral regression kernel discriminant analysis

“…This algorithm is implemented on Matlab and becomes famous due to its available open-source implementation. The algorithm has four stages: Haar feature selection, creating an integral image, Adaboost training, and cascading classifiers [21]. After face detection step, histogram equalisation is performed, it usually increases the global contrast of the images, especially when the usable data of the image is represented by close contrast values.…”

“…It is based on the principle that they are darker than other part in the face image. It searches small patches which are approximately as large as an eye and are darker than their neighbourhoods [21]. After eyes are detected, the left and right eyes are separated and iris segmentation is performed by Daugman's algorithm.…”

Performance Comparison of Feature Face Detection Algorithm on The Embedded Platform

“…Therefore, the face is the most accurate indicator for face detection [13] [14]. On the machine, human face detection is done by distinguishing the pattern of face shape from other patterns on the camera frame [15] [16]. The machine will group numerical and symbolic data on facial features in the digital image automatically to obtain descriptive data on the pattern of a face [17].…”