Matting Technique Research Articles

Image Matting With Deep Gaussian Process.

We observe a common characteristic between the classical propagation-based image matting and the Gaussian process (GP)-based regression. The former produces closer alpha matte values for pixels associated with a higher affinity, while the outputs regressed by the latter are more correlated for more similar inputs. Based on this observation, we reformulate image matting as GP and find that this novel matting-GP formulation results in a set of attractive properties. First, it offers an alternative view on and approach to propagation-based image matting. Second, an application of kernel learning in GP brings in a novel deep matting-GP technique, which is pretty powerful for encapsulating the expressive power of deep architecture on the image relative to its matting. Third, an existing scalable GP technique can be incorporated to further reduce the computational complexity to O(n) from O(n3) of many conventional matting propagation techniques. Our deep matting-GP provides an attractive strategy toward addressing the limit of widespread adoption of deep learning techniques to image matting for which a sufficiently large labeled dataset is lacking. A set of experiments on both synthetically composited images and real-world images show the superiority of the deep matting-GP to not only the classical propagation-based matting techniques but also modern deep learning-based approaches.

Penguatan Proses Belajar Mengajar Melalui Penggunaan Teknik Place Mat

Teaching and learning process is inseparable from method and technique applied by educators, especially teachers as an attempt to improve the quality of output learning. Place mat technique is one of the cooperative learning methods in which students could work by themselves first and then team up with other group’s members in solving an issue or topic given. They can write down their idea as well as group’s opinion in a big place mat paper. Through the initial observation by interviewing some teachers of SMAN 1 Kuta Baro, Aceh Besar (Great aceh), it was found out that most of them never use this kind of technique in the classroom setting; they use some other kinds of techniques such as role play, jigsaw, numbered head together, and conventional technique. Therefore, the writers intend to carry on a community service to the students in the school as an effort to vary and increase the quality of teaching and learning process. This community service is hold on October 5-7, 2022 in SMAN 1 Kuta Baro, Great Aceh. This service is meant to train those teachers to be able to apply the technique during the teaching. Then, it is suggested to further community service activists to do the same activity in the rural areas as they basically need more input and insight from other educators in upgrading the way they teach.

Graph convolutional network‐based image matting algorithm for computer vision applications

Image matting plays a vital role in a variety of computer vision tasks including video editing and image fusion. Previously presented image matting algorithms might fail in producing favorable results since most of them concentrate on the similarity between the neighboring pixels while neglecting the corresponding spatial relationship. To address this issue, an end-to-end image matting framework through leveraging deep learning mechanism and graph theory is proposed. The proposed pipeline is a concatenation of one deep feature extraction component and a Graph Convolutional Network (GCN). The former part takes an image and its corresponding trimap as inputs and can generate the pixel-wise features, which are then exploited as the input of the GCN locating at the latter part of the proposed framework. The GCN would refine the features for every pixel and predict the alpha matte outcome of the image. The approach outperforms a group of state-of-the-art matting techniques as shown by the theoretical analysis and experimental results in terms of both accuracy and visual effects.

Multi-focus image fusion based on fractional order differentiation and closed image matting

This paper presents a novel approach to addressing the fusion of multi-focus images in either registered or mis-registered cases. The conventional approaches often produce blurred edges of objects in the fused images due to inaccurate decision maps. On the other hand, these decision maps are sensitive to mis-registration that causes artifact in the fused images. Therefore, we propose a robust multi-focus image fusion approach with clear object edges for the registered or mis-registered source images. In this approach, a fractional order differential mask is creatively adopted to pre-process the source images, ensuring the initial decision maps both with the boundaries and fine structures of the objects and with the internal holes closed. Then, the closed matting technique, in lieu of the robust matting, is adopted to refine the initial decision maps. This significantly reduces the interaction information from the users, but still preserves the complete boundaries of the objects. Finally, the global threshold processing is skillfully adopted to form the decision maps. This not only yields the final decision maps with smooth boundaries, but also guarantees the rich gradient information from the mis-registered source images. The experimental results show that the designed algorithm provides better visual perception and higher objective evaluation than some existing representative algorithms.

Image Matting: A Comprehensive Survey on Techniques, Comparative Analysis, Applications and Future Scope

In the era of rapid growth of technologies, image matting plays a key role in image and video editing along with image composition. In many significant real-world applications such as film production, it has been widely used for visual effects, virtual zoom, image translation, image editing and video editing. With recent advancements in digital cameras, both professionals and consumers have become increasingly involved in matting techniques to facilitate image editing activities. Image matting plays an important role to estimate alpha matte in the unknown region to distinguish foreground from the background region of an image using an input image and the corresponding trimap of an image which represents a foreground and unknown region. Numerous image matting techniques have been proposed recently to extract high-quality matte from image and video sequences. This paper illustrates a systematic overview of the current image and video matting techniques mostly emphasis on the current and advanced algorithms proposed recently. In general, image matting techniques have been categorized according to their underlying approaches, namely, sampling-based, propagation-based, combination of sampling and propagation-based and deep learning-based algorithms. The traditional image matting algorithms depend primarily on color information to predict alpha matte such as sampling-based, propagation-based or combination of sampling and propagation-based algorithms. However, these techniques mostly use low-level features and suffer from high-level background which tends to produce unwanted artifacts when color is same or semi-transparent in the foreground object. Image matting techniques based on deep learning have recently introduced to address the shortcomings of traditional algorithms. Rather than simply depending on the color information, it uses deep learning mechanism to estimate the alpha matte using an input image and the trimap of an image. A comprehensive survey on recent image matting algorithms and in-depth comparative analysis of these algorithms has been thoroughly discussed in this paper.

The Yoga Mat Technique in Postless Hip Arthroscopy

Hip arthroscopy for the treatment of femoroacetabular impingement syndrome with anti-sliding techniques and without the use of a perineal post to achieve hip distraction has increased greatly in the past 5 to 10 years. To access the hip joint, distraction is mandatory to treat intra-articular disorders such as labral tears, acetabular cartilage defects, loose bodies, ligamentum teres tears, and avascular necrosis of the hip. In hip distraction, counter-distraction is needed, and this is achieved with a bulky and cushioned perineal post. Most of the described techniques in hip arthroscopy worldwide use a perineal post, but iatrogenic pudendal nerve, genital lacerations, hematomas, and groin complications have been reported to occur. In Latin American countries, disposable hip pad devices are expensive, and not all the arthroscopic companies provide them. Our yoga mat technique provides enough countertraction to achieve adequate hip distraction. Labral repair, labral reconstruction, and decompression of femoroacetabular impingement syndrome have been achieved properly, reliably, and reproducibly, and no Trendelenburg position is needed. Postless hip arthroscopy is made simple, and positioning the patient is not difficult. Hip surgeons can adapt this technique to a fracture table, a hip distractor, and a standard operating room table.

Fuzzy based iterative matting technique for underwater images

Fuzzy based iterative matting technique for underwater images

JMNet: A joint matting network for automatic human matting

We propose a novel end-to-end deep learning framework, the Joint Matting Network (JMNet), to automatically generate alpha mattes for human images. We utilize the intrinsic structures of the human body as seen in images by introducing a pose estimation module, which can provide both global structural guidance and a local attention focus for the matting task. Our network model includes a pose network, a trimap network, a matting network, and a shared encoder to extract features for the above three networks. We also append a trimap refinement module and utilize gradient loss to provide a sharper alpha matte. Extensive experiments have shown that our method outperforms state-of-theart human matting techniques; the shared encoder leads to better performance and lower memory costs. Our model can process real images downloaded from the Internet for use in composition applications.

Single image dehazing by approximating and eliminating the additional airlight component

This paper proposes a novel technique for single image dehazing using adaptive nearest neighbor regularization to obtain a haze-free transmission map and then approximating the additional airlight component present in the hazy image. The proposed method relies on the intensity distribution in the small image patches of the image, exhibited from the Y channel of the YCbCr representation of the image, in order to preserve the texture information of the image. We substitute the commonly used soft matting technique in assessing the refined transmission map for haze removal, by adaptive nearest neighbor classifier. We assume that the actual color of the haze-free pixels in the image is approximated by a set of discrete colors. We discover the haze-free pixels using the Nearest-Neighbor (NN) regularization. Finally, unlike the state-of-the-art methods, we approximate the additional airlight present in the image patch and eliminate that to clear the haze, instead of estimating the transmission of the medium. The proposed nearest neighbor regularization technique automatically changes the patch size, which helps in dealing with the high depth region (e.g., sky region) of the image. We experimented on standard synthetic and real hazy image datasets and observed that, the proposed method outperforms the state-of-the-art, especially for images with sky regions.

Shadow Detection and Removal for Occluded Object Information Recovery in Urban High-Resolution Panchromatic Satellite Images

The existence of shadows in very high-resolution panchromatic satellite images can occlude some objects to cause the reduction or loss of their information, particularly in urban scenes. To recover the occluded information of objects, shadow removal is a significant processing procedure for the image interpretation and application. In this paper, we propose a novel framework of shadow detection and removal for panchromatic satellite images to restore the obscured object information. In shadow detection, we present an automatic soft shadow detection method by the combined application of a bimodal histogram splitting method and image matting technique. Soft detection results can exhibit both umbra areas and penumbra areas to describe the shadow distribution precisely. In shadow removal, we propose a spatial adaptive nonlocal sparse shadow removal method to operate at two levels. For the initial step, we apply the line correction method to enhance shadow areas roughly in global. In the refined process, we study the characteristics of objects and shadows, and analyze spatial relationship between them. The second linear radiometric correction and nonlocal sparse model are used to simultaneously control the brightness and smoothness of the recovered shadow areas to be the same as the corresponding nonshadow areas based on group matrix with similar patches. Our method can restore the uniform objects in the shadow areas. High-resolution panchromatic shadow images of different cases and different satellites are processed by the proposed method. The experimental results verify the effectiveness and superiority of the proposed method by comparing three other methods.

Shadow Detection and Removal Using Tri-Class Based Thresholding and Shadow Matting Technique

Shadow detection and removal in real scene images are always a significant problem. This work aims to address the problem of shadow detection and removal from urban high resolution remote sensing images. To detect shadow from images a pre processing step is performed. Triclass Thresholding technique is used for segmentation and it is based on Otsu's method. Using this iterative method the images are separated into three classes that are foreground region, background region and to-be-determined region. Then Otsu's method is applied only to to-be-determined region iteratively. After segmentation shadow in the images are detected using bimodal histogram splitting method. Then the false shadow including water bodies, vegetation and some dark objects are eliminated by considering spectral and geometric features. Also an additional method called pair wise region based detection is used to accurately detect the shadow. So image is clustered by using K-mean Algorithm and to detect shadow by comparing colour and the ratio of intensities in the adjacent pair. Finally shadow matting called soft matting technique is used to obtain shadow free image. Results show that the new method accurately detects shadow and can efficiently restore shadow with 90.57% accuracy.

A Scheme for Increasing Visibility of Single Hazy Image under Night Condition

This paper proposes an approach for Increasing visibility of single hazy image under night condition which utilizes a combination of histogram equalization, gamma correction, and dark channel prior with soft matting technique, refined transmission procedure to avoid the generation of block artifacts in the restored image, and effective transmission map estimation by adjusting its intensity via an enhanced transmission procedure based on the adaptive gamma correction technique. Our result shows better contrast noise ratio and peak signal to noise ratio values over existing methods based on dark channel prior.

The Mechanical Properties of Ukam Fibre-Reinforced Cashew Nut Shell Resin Composite

The mechanical properties of ukam fibre cashew nut shell resin composite were studied for possible structural application in engineering. Basically, the hand lay-up method was employed to manufacture the test samples of the composite by 40:60 weight ratio and testing the samples' mechanical properties using the instron tensile machine and the izod impact machine respectively. Consequently, the experiments demonstrated that the ukam fibre reinforced cashew nut shell resin composite has a maximum tensile strength of 40.5MPa, the impact energy of 1.93J and a young tensile modulus of 1GPa. The above results indicate that ukam fibre- reinforced cashew nut shell resin composite is suited for low cost applications in engineering and is a good alternative to artificial glass fibres. The matrix-fibre stress transfer and the fabrication technique will determine the effectiveness of natural fibre composite (3). In this research, the hand lay-up technique was adopted to produce ukam fibre- reinforced cashew nut shell resin samples whose mechanical properties were determined. The investigation of the ukam fibre- reinforced cashew nut shell resin composite has drawn much attention due to ukam fibre increased trials in the Eastern Nigeria. The study also used simple manufacturing methods for fabricating the laminates with a view to recycling the composite. 1. Materials and Methods 1.1 Materials 1.1.1 Cashew Nut Shell Liquid The cashew nut used in this study was sourced locally, precisely from Obollo-Afor market of Nsukka, Nigeria. The processing was done using the hot method of extraction. 1.1.2 Ukam Plant Fibres The ukam plant also was sourced locally from farmers inNsukka area of Enugu state, Nigeria. The water retting processing method was employed. The required surface treatment and modification were carried out using saline solution, sodium hydroxide solution and acetic acids. The chopped strand matting technique was used because of its

Mutifidus in Spinal Stability: Analysis of Inhibition with Muscle Activation Techniques

Objectives: To (1) study the relationship between multifidus muscle activation and perception, (2) to explore the correlation between the failure of the multifidus and back pain, when (3) tested with the MAT technique and back pain questionnaire.

Automatic segmentation improvement based on parameter-free spectral matting

In this study, we propose a parameter-free spectral matting technique to automatically achieve essential matting components from the smallest eigenvectors of a Laplacian matrix that accomplish good segmentation results in photography. The proposed scheme is based on discarding alpha components before grouping alpha mattes for high accuracy and better performance in segmentation and compositing. The scheme’s emphasis is on finding the best alpha components of the foreground through opacity estimation in natural photographs without any required user input. The said parameter-free spectral matting technique gives us better performance in terms of seamless boundaries than the existing segmentation techniques. We have compared our scheme with the state-of-the-art interactive segmentation and matting techniques, that is, GrabCut, Graph Cut, and Bayesian Matting, etc. The results of the proposed parameter-free spectral matting scheme are promising and affirm the effectiveness of our method.

Evaluation of motion symmetry in overweight cats with osteoarthritis in the stifle joint using a pressure sensitive mat technique

An increasing number of cats are being recognized as overweight. Overweight is known to aggravate painful musculoskeletal conditions. Osteoarthritis (OA) is one of the most common musculoskeletal conditions that cause chronic pain in cats.

A Hybrid Approach for Dehazing Images

Bad weather conditions including haze, fog, rain etc. degrade the picture quality which causes poor visualizations. Various methods have been proposed to eradicate the effects of above conditions. Initially, polarization filters were used to restore the foggy image. Though this method estimates airlight to quite good an extent but at the same time uses multiple images therefore, cannot be applied on dynamic scenes. In addition, it has very high time complexity. To overcome the use of multiple images Dark channel prior technique was used that effectively calculates the transmission map to restore the foggy image. For this purpose it requires usage of soft matting technique that causes halo effect and has high time complexity. We are of the opinion that if transmission map is calculated using dark channel prior and airlight is estimated using polarisation filters, the resultant process will not only have lower time complexity but at the same time overcomes the drawback of multiple images. The above mentioned technique is implemented in MATLAB-9 and analysed in this paper. The results shows that usage of this hybrid approach gives quite better results.

Survey of the Parasite Toxoplasma gondii in Human Consumed Ovine Meat in Tunis City

Toxoplasmosis has been recognized as parasitic zoonosis with the highest human incidence. The human infection by the parasite can lead to severe clinical manifestations in congenital toxoplasmosis and immunocompromised patients. Contamination occurs mainly by foodborne ways especially consumption of raw or undercooked meat. In contrast to other foodborne infections, toxoplasmosis is a chronic infection which would make its economic and social impact much higher than even previously anticipated. Ovine meat was advanced as a major risk factor, so we investigated its parasite survey, under natural conditions. Serological MAT technique and touchdown PCR approaches were used for prevalence determination of the parasite in slaughtered sheep intended to human consumption in Tunis City. The genotyping was carried by SNPs analysis of SAG3 marker. Anti-Toxoplasma antibodies were present in 38.2% of young sheep and in 73.6% of adult sheep. Molecular detection revealed the contamination of 50% of ewes’ tissue. Sequencing and SNPs analysis enabled unambiguous typing of meat isolates and revealed the presence of mixed strains as those previously identified from clinical samples in the same area. Our findings conclude that slaughtered sheep are highly infected, suggesting them as a major risk factor of Toxoplasma gondii transmission by meat consumption. Special aware should target consequently this factor when recommendations have to be established by the health care commanders.

KNN Matting

This paper proposes to apply the nonlocal principle to general alpha matting for the simultaneous extraction of multiple image layers; each layer may have disjoint as well as coherent segments typical of foreground mattes in natural image matting. The estimated alphas also satisfy the summation constraint. As in nonlocal matting, our approach does not assume the local color-line model and does not require sophisticated sampling or learning strategies. On the other hand, our matting method generalizes well to any color or feature space in any dimension, any number of alphas and layers at a pixel beyond two, and comes with an arguably simpler implementation, which we have made publicly available. Our matting technique, aptly called KNN matting, capitalizes on the nonlocal principle by using $(K)$ nearest neighbors (KNN) in matching nonlocal neighborhoods, and contributes a simple and fast algorithm that produces competitive results with sparse user markups. KNN matting has a closed-form solution that can leverage the preconditioned conjugate gradient method to produce an efficient implementation. Experimental evaluation on benchmark datasets indicates that our matting results are comparable to or of higher quality than state-of-the-art methods requiring more involved implementation. In this paper, we take the nonlocal principle beyond alpha estimation and extract overlapping image layers using the same Laplacian framework. Given the alpha value, our closed form solution can be elegantly generalized to solve the multilayer extraction problem. We perform qualitative and quantitative comparisons to demonstrate the accuracy of the extracted image layers.

Background subtraction driven seeds selection for moving objects segmentation and matting

In this paper, we address the difficult task of moving objects segmentation and matting in dynamic scenes. Toward this end, we propose a new automatic way to integrate a background subtraction (BGS) and an alpha matting technique via a heuristic seeds selection scheme. Specifically, our method can be divided into three main steps. First, we use a novel BGS method as attention mechanisms, generating many possible foreground pixels by tuning it for low false-positives and false-negatives as much as possible. Second, a connected components algorithm is used to give the bounding boxes of the labeled foreground pixels. Finally, matting of the object associated to a given bounding box is performed using a heuristic seeds selection scheme. This matting task is guided by top-down knowledge. Experimental results demonstrate the efficiency and effectiveness of our method.