Head pose classification is widely used for the preprocessing before face recognition and multi-angle problems, because algorithms such as face recognition often require the input image to be a front face. But affected by the COVID-19 pandemic, people wear face masks to protect themselves safe, which makes cover most areas of the face. This makes some common algorithms cannot be applied to head pose classification in the new situation. Therefore, this paper established a method HGL to deal with the head pose classification by adopting color texture analysis of images and line portrait. The proposed HGL method combines the Hchannel of the HSV color space with the face portrait and grayscale image, and train the CNN to extract features for classification. The evaluation on MAFA dataset shows that compared with the algorithms based on facial landmark detection and convolutional neural network, the proposed method has achieved a better performance (Front accuracy: 93.64%, Side accuracy: 87.17%).
Head pose classification is widely used for the preprocessing before face recognition and multi-angle problems, because algorithms such as face recognition often require the input image to be a front face. But affected by the COVID-19 pandemic, people wear face masks to protect themselves safe, which makes cover most areas of the face. This makes some common algorithms cannot be applied to head pose classification in the new situation. Therefore, this paper established a method HGL to deal with the head pose classification by adopting color texture analysis of images and line portrait. The proposed HGL method combines the Hchannel of the HSV color space with the face portrait and grayscale image, and train the CNN to extract features for classification. The evaluation on MAFA dataset shows that compared with the algorithms based on facial landmark detection and convolutional neural network, the proposed method has achieved a better performance (Front accuracy: 93.64%, Side accuracy: 87.17%).
“…(6):Tbadbreakafter=madaptivegoodbreakafter+kσbadbreakafter+βmwindow2σ where σ is the image standard deviation, β is an adaptive factor set in the range of 0–30, and madaptive is an adaptive mean value that can be defined as follows:madaptivebadbreakafter=mglobalbadbreakafter+mwindow2 where mglobal is the mean value of the image and mwindow is the mean value of the local window. Based on our experiments, we found that the most appropriate local window is 21 x 21 pixels; moreover, k is defined as follows: [7]kbadbreakafter=badbreakafter−σfalse(255badbreakafter−32σfalse) while σ is the standard deviation of the image window. After binarization, the unwanted object is removed in the removing artifact stage.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…A thresholding based approach is the most straightforward binarization technique; however, it fails for binarizing documents that have severe and complex degradation. Some modified thresholding methods such as Bataineh [6] and iNICK [7] were proposed to enhance the binarization performance but issues still remain.Figure 1Examples of ancient documents suffering from combinations of degradation types. (a) Document suffering from a combination of ink-bleed through, faint text, and yellowing background.…”
Document image binarization is a challenging task because of combined degradation in a document. In this study, a new binarization method is proposed for binarizing an ancient document with combined degradation. The proposed method comprises the following four stages: histogram analysis, contrast enhancement, local adaptive thresholding, and artifact removal. In histogram analysis, a new approach is applied to establish a uniform background. Next, the image contrast is enhanced using a new contrast enhancement, and then the document is binarized using a novel local adaptive thresholding. Artifacts from the binarization process are removed in the artifact removal stage. Finally, an experiment is conducted using one private and four public datasets and by simulating the proposed method with and without contrast enhancement. The results showed that the proposed method is faster and more effective compared to other state-of-the-art procedures for binarizing ancient documents.
“…dev. Sauvola [146] Local threshold Improvement on Niblack Wolf [173] Local threshold Improvement on Sauvola with global normalization Gatos [38] Local threshold Threshold after background removal NICK [64] Local threshold Adapts Niblack based on global mean Bataineh [10] Local threshold Threshold based on local and global statistics Saddami [144] Local threshold Adaptively sets k in NICK based on global std. dev.…”
Section: Otsumentioning
confidence: 99%
“…Bataineh et al [10] proposed a local threshold computed from both the local and global means and standard deviations that was shown to outperform NICK on DIBCO 2009, though parameters were not necessarily tuned for NICK. Adaptively setting the k value in NICK thresholding based on the global standard deviation was shown to improve performance over a fixed k [144].…”
This review provides a comprehensive view of the field of historical document image binarization with a focus on the contributions made in the last decade. After the introduction of a standard benchmark dataset with the 2009 Document Image Binarization Contest, research in the field accelerated. Besides the standard methods for image thresholding, preprocessing, and post-processing, we review the literature on methods such as statistical models, pixel classification with learning algorithms, and parameter tuning. In addition to reviewing binarization algorithms, we discuss the available public datasets and evaluation metrics, including those that require pixel-level ground truth and those that do not. We conclude with recommendations for future work.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
