This paper presents an improved face detection method for color images. We propose a boosted skin-color model in RGB space which can reduce more effectively noises forming from similar skin colors. With our solution, ...
详细信息
ISBN:
(纸本)9788995003848
This paper presents an improved face detection method for color images. We propose a boosted skin-color model in RGB space which can reduce more effectively noises forming from similar skin colors. With our solution, we receive more reasonable skin detection for different human races. We modifed localbinary Pattern (LBP) by adding a set of spatial templates. This LBP considers both principal local shapes and spatial textures of facial components. Human face is represented by LBP histogram. Moreover, the grayscale image of human face is changed to Discrete Cosine Transform (DCT) coefficients used in embedded Hidden Markov Models (eHMMs). A modified LBP (mLBP) histogram matching and eHMMs are composed to hierarchical classifier to determine whether skin regions are faces or not. The experiments show that our method performs a better capability for face detection in complex environments than using separately eHMMs or LBP histogram. The correct face detection rate of proposed system is over 94% among our test database which consists totally 485 single and multi-face color images of 1429 persons in different lighting conditions, face rotations, occlusions and complex backgrounds from different sources: Caltech face database, Sumgmug image library, family photos, personal digital images and world wide web.
In the medical domain, experts usually look at specific anatomical structures to identify the cause of a pathology, and therefore they can largely benefit from automated tools that retrieve relevant slice(s) from a pa...
详细信息
ISBN:
(纸本)9781424417650
In the medical domain, experts usually look at specific anatomical structures to identify the cause of a pathology, and therefore they can largely benefit from automated tools that retrieve relevant slice(s) from a patient's image volume in diagnosis. Accordingly, this paper introduces a novel search and retrieval work for finding relevant slices in brain MR (magnetic resonance) volumes. As intensity is non-standard in MR we explore performance of two complementary intensity invariant features, local binary patterns and Kanade-Lucas-Tomasi feature points, their extended versions with spatial context, and a simple edge descriptor with spatial context. Experiments on real and simulated data showed that the local binary patterns with spatial context is fast, highly accurate, and robust to geometric deformations and intensity variations.
This paper proposes the use of the combination of digital curvelet transform and local binary patterns for recognizing facial expressions from still images. The curvelet transform is applied to the image of a face at ...
详细信息
ISBN:
(纸本)9781424442966
This paper proposes the use of the combination of digital curvelet transform and local binary patterns for recognizing facial expressions from still images. The curvelet transform is applied to the image of a face at a specific scale and orientation. local binary patterns are extracted from the selected curvelet sub-bands to form the descriptive feature set of the expressions. The average of the features of a particular class of expression is considered as the representative feature set of that class. The expression recognition is performed using a nearest neighbor classifier with Chi-square as the dissimilarity metric. Experiments show that our method yields recognition rates of 93% and 90% in JAFFE and Cohn-Kanade databases respectively.
One of the most challenging factors in face recognition is pose variation. This paper proposes an appropriate framework to identify images across pose. The input profile image is classified to a pose range. After that...
详细信息
ISBN:
(纸本)9783319184760;9783319184753
One of the most challenging factors in face recognition is pose variation. This paper proposes an appropriate framework to identify images across pose. The input profile image is classified to a pose range. After that, this image is matched with the same pose range images from a certain database to determine its identification. In this framework, descriptors which are based on local binary patterns are used to extract features of all images. Experiments on the FERET database prove the robustness of the proposed framework based on comparison with other approaches.
The images of lace textile are particularly difficult to be analyzed in digital form using classical image processing techniques. The major reasons of this difficulty emerge from the complex nature of lace which gener...
详细信息
ISBN:
(纸本)9781479970698
The images of lace textile are particularly difficult to be analyzed in digital form using classical image processing techniques. The major reasons of this difficulty emerge from the complex nature of lace which generally has different textures in its constituents like the background and patterns. In this paper, we study the behavior of Image Histogram (HistI) and local binary patterns (LBP) on image extracts of lace in presence and absence of rotation. We further evaluate two variants of LBP;primarily the LBP Histogram (LBPB) and secondly the Fourier Transform applied on the LBP Histogram (LBPFFT). Consequently, we analyze the contribution of data fusion on feature level and score level in the different experimentations. The classification rate evaluates the discrimination degree of each descriptor via the k nearest neighbors kNN classifier. Experimental results indicate that the LBPB, LBPFFT and HistI combined at score level generate the better performance in absence of transformations. Whereas, LBPFFT and HistI combined at the same level generate the better classification rate, in the presence of rotation.
Texture-based method (TBM) using local binary patterns (LBP) proposed in ill is a successful solution to background subtraction especially for dynamic background scenes. However, it usually suffers from inaccuracy of ...
详细信息
ISBN:
(纸本)9781424441303
Texture-based method (TBM) using local binary patterns (LBP) proposed in ill is a successful solution to background subtraction especially for dynamic background scenes. However, it usually suffers from inaccuracy of the shapes of segmentation results and slow adaptation to the current situation. In this paper, we present an improved TBM that solves the two problems. To solve the first problem, a spatially weighted LBP histogram (SWLH) is proposed to be the feature vector and a simple shadow removing method is introduced. When dealing with the second one, we use an adaptive learning rate for each model LBP histogram and maintain multiple frame level models to process sudden illumination changes. Experimental results show that the proposed method outperforms the original TBM.
Automatic facial expression analysis is an interesting and challenging problem which impacts important applications in many areas such as human-computer interaction and data-driven animation. Deriving effective facial...
详细信息
ISBN:
(纸本)9781479900336;9781479900312
Automatic facial expression analysis is an interesting and challenging problem which impacts important applications in many areas such as human-computer interaction and data-driven animation. Deriving effective facial representative features from face images is a vital step towards successful expression recognition. In this paper, we evaluate facial representation based on statistical local features called local binary patterns (LBP) for facial expression recognition. Simulation results illustrate that LBP features are effective and efficient for facial expression recognition. A real-time implementation of the proposed approach is also demonstrated which can recognize expressions accurately at the rate of 4.8 frames per second.
In this paper, we propose a novel approach for binary image reconstruction from few projections. The binary reconstruction problem can be highly underdetermined and one way to reduce the search space of feasible solut...
详细信息
ISBN:
(纸本)9783030298883;9783030298876
In this paper, we propose a novel approach for binary image reconstruction from few projections. The binary reconstruction problem can be highly underdetermined and one way to reduce the search space of feasible solutions is to exploit some prior knowledge of the image to be reconstructed. We use texture information extracted from sample image patches as prior knowledge. Experimental results show that this approach can retain the structure of the image even if just a very few number of projections are used for the reconstruction.
In this paper, we propose a new texture descriptor GLBP (Gradient LBP) for age group estimation. LBP exploits the only signs of the gradients between a center pixel and its surrounding pixels in a local patch and it d...
详细信息
ISBN:
(纸本)9781479945917
In this paper, we propose a new texture descriptor GLBP (Gradient LBP) for age group estimation. LBP exploits the only signs of the gradients between a center pixel and its surrounding pixels in a local patch and it does not reflect their magnitudes. This fails LBP to describe local signal structure in detail. Motivated by this observation, we propose so called GLBP, which considers the magnitude as well as the sign of the gradient. Experimental results show that when the proposed method is applied to age group estimation, it can achieve higher classification rate than existing well-known texture descriptors.
A novel medical image retrieval algorithm based on texture is proposed. The contourlet transform combines nonseparable and directional filters banks, and has multiscale and directional properties. The marginal distrib...
详细信息
ISBN:
(纸本)9781424427994
A novel medical image retrieval algorithm based on texture is proposed. The contourlet transform combines nonseparable and directional filters banks, and has multiscale and directional properties. The marginal distribution of contourlet transform coefficients is modeled by generalized Gaussian density. It is used for texture feature extraction in transform domain. Uniform local binary patterns have good rotation invariance. It extracts texture feature in spatial domain and his retrieval time is short. A texture feature extracting algorithm combined statistical features of the contourlet with block-based uniform local binary patterns is proposed further. The two texture feature were extracted in spatial domain and in transform domain, which are complementary. A database of medical images was retrieved by this algorithm. The result shows it can achieve a high precision of retrieval.
暂无评论