Lin-Lin Huang

Learn More
Both detection accuracy and speed are of major concerns in developing a robust face detection system for real-world applications. To this end, we propose a robust face detection approach by combining multiple experts in both cascade and parallel manner. We design three detection experts which employ different feature representation schemes of local images:(More)
In this paper, we propose a new method for face detection from cluttered images. We use a polynomial neural network (PNN) for separation of face and non-face patterns while the complexity of the PNN is reduced by principal component analysis (PCA). In face detection, the PNN is used to classify sliding windows in multiple scales and label the windows that(More)
Face detection from cluttered images is challenging due to the wide variability of face appearances and the complexity of image backgrounds. This paper proposes a classi"cation-based method for locating frontal faces in cluttered images. To improve the detection performance, we extract gradient direction features from local window images as the input of the(More)
AIM The homeobox gene Barx2 was recently identified as a regulator of ovarian and breast cancer; however, the expression level of BARX2 and its significance in hepatocellular carcinoma (HCC) remain unknown. METHODS Protein and mRNA expression levels of Barx2 were examined using Western blotting and real-time PCR respectively, in paired HCC tissue and(More)
Ascites is the pathologic accumulation of fluid within the peritoneal cavity. Because many diseases can cause ascites, in particular cirrhosis, samples of ascitic fluid are commonly analyzed in order to develop a differential diagnosis. The concept of transudate versus exudate, as determined by total protein measurements, is outdated and the use of(More)
Face detection from cluttered images is very challenging due to the diverse variation of face appearance and the complexity of image background. In this paper, we propose a neural network based approach for locating frontal views of human faces in cluttered images. We use a radial basis function network (RBFN) for separation of face and non-face patterns(More)