High Efficiency Video Coding (HEVC) has a better coding efficiency comparing with H.264/AVC. However, performance enhancement results in increased computational complexity which is mainly brought by the quadtree based coding tree unit (CTU). In this paper, an early termination algorithm based on AdaBoost classifier for coding unit (CU) is proposed to accelerate the process of searching the best partition for CTU. Experiment results indicate that our method can save 39% computational complexity on average at the cost of increasing Bjontegaard-Delta rate (BD-rate) by 0.18.

Protein-Protein Interaction Extraction (PPIE) from biomedical literatures is an important task in biomedical text mining and has achieved great success on public datasets. However, in real-world applications, the existing PPI extraction methods are limited to label effort. Therefore, transfer learning method is applied to reduce the cost of manual labeling. Current transfer learning methods suffer from negative transfer and lower performance. To tackle this problem, an improved TrAdaBoost algorithm is proposed, that is, relative distribution is introduced to initialize the weights of TrAdaBoost to overcome the negative transfer caused by domain differences. To make further improvement on the performance of transfer learning, an approach combining active learning with the improved TrAdaBoost is presented. The experimental results on publicly available PPI corpora show that our method outperforms TrAdaBoost and SVM when the labeled data is insufficient,and on document classification corpora, it also illustrates that the proposed approaches can achieve better performance than TrAdaBoost and TPTSVM in final, which verifies the effectiveness of our methods.

Object detection is at the heart of nearly all the computer vision systems. Standard off-the-shelf embedded processors are hard to meet the trade-offs among performance, power consumption and flexibility required by object detection applications. Therefore, this paper presents an Application Specific Instruction set Processor (ASIP) for object detection using AdaBoost-based learning algorithm with Haar-like features as weak classifiers. Algorithm optimizations are employed to reduce memory bandwidth requirements without losing reliability. In the proposed ASIP, Single Instruction Multiple Data (SIMD) architecture is adopted for fully exploiting data-level parallelism inherent to the target algorithm. With adding pipeline stages, application-specific hardware components and custom instructions, the AdaBoost algorithm is accelerated by a factor of 13.7x compared to the optimized pure software implementation. Compared with ARM946 and TMS320C64+, our ASIP shows 32x and 7x better throughput, 10x and 224x better area efficiency, 6.8x and 18.8x better power efficiency, respectively. Furthermore, compared to hard-wired designs, evaluation results show an advantage of the proposed architecture in terms of chip area efficiency while maintain a reliable performance and achieve real-time object detection at 32fps on VGA video.

Gentle AdaBoost is widely used in object detection and pattern recognition due to its efficiency and stability. To focus on instances with small margins, Gentle AdaBoost assigns larger weights to these instances during the training. However, misclassification of small-margin instances can still occur, which will cause the weights of these instances to become larger and larger. Eventually, several large-weight instances might dominate the whole data distribution, encouraging Gentle AdaBoost to choose weak hypotheses that fit only these instances in the late training phase. This phenomenon, known as “classifier distortion”, degrades the generalization error and can easily lead to overfitting since the deviation of all selected weak hypotheses is increased by the late-selected ones. To solve this problem, we propose a new variant which we call “Penalized AdaBoost”. In each iteration, our approach not only penalizes the misclassification of instances with small margins but also restrains the weight increase for instances with minimal margins. Our method performs better than Gentle AdaBoost because it avoids the “classifier distortion” effectively. Experiments show that our method achieves far lower generalization errors and a similar training speed compared with Gentle AdaBoost.

One of the major applications of contrast-enhanced ultrasound (CEUS) is lesion classification. After contrast agents are administered, it is possible to identify a lesion type from its enhancement pattern. However, CEUS image reading is not easy because there are various types of enhancement patterns even for the same type of lesion, and clear classification criteria have not yet been defined. Some studies have used conventional time intensity curves (TICs), which show the vessel dynamics of a lesion. It is possible to predict lesion type from the TIC parameters, such as the coefficients obtained by curve fitting, peak intensity, flow rate and time to peak. However, these parameters are not always provide sufficient accuracy. In this paper, we prepare 1D Haar-like features which describe intensity changes in a TIC and adopt the Adaboost machine learning technique, which eases understanding of which features are useful. Hyperparameters of weak classifiers, e.g., the step size of a Haar-like filter length and threshold for output of the filter, are optimized by searching for those parameters that give the best accuracy. We evaluate the proposed method using 36 focal splenic lesions in canines 16 of which were benign and 20 malignant. The accuracies were 91.7% (33/36) when inspected by an experienced veterinarian, 75.0% (27/36) by linear discriminant analysis (LDA) using conventional three TIC parameters: time to peak, area under curve and peak intensity, and 91.7% (33/36) using our proposed method. McNemar testing shows the p-value to be less than 0.05 between the proposed method and LDA. This result shows the statistical significance of differences between the proposed method and the conventional TIC analysis method using LDA.

Recently, video surveillance systems have been widely introduced in various places, and protecting the privacy of objects in the scene has been as important as ensuring security. Masking each moving object with a background subtraction method is an effective technique to protect its privacy. However, the background subtraction method is heavily affected by sunshine change, and a redundant masking by over-extraction is inevitable. Such superfluous masking disturbs the quality of video surveillance. In this paper, we propose a moving object masking method combining background subtraction and machine learning based on Real AdaBoost. This method can reduce the superfluous masking while maintaining the reliability of privacy protection. In the experiments, we demonstrate that the proposed method achieves about 78-94% accuracy for classifying superfluous masking regions and moving objects.

We implement external memory-free deep pipelined FPGA implementation including HOG feature extraction and AdaBoost classification. To construct our design by compact FPGA, we introduce some simplifications of the algorithm and aggressive use of stream oriented architectures. We present comparison results between our simplified fixed-point scheme and an original floating-point scheme in terms of quality of results, and the results suggest the negative impact of the simplified scheme for hardware implementation is limited. We empirically show that, our system is able to detect human from 640480 VGA images at up to 112 FPS on a Xilinx Virtex-5 XC5VLX50 FPGA.

In this paper, we propose a pedestrian detection algorithm based on both appearance and motion features to achieve high detection accuracy when applied to complex scenes. Here, a pedestrian's appearance is described by a histogram of oriented spatial gradients, and his/her motion is represented by another histogram of temporal gradients computed from successive frames. Since pedestrians typically exhibit not only their human shapes but also unique human movements generated by their arms and legs, the proposed algorithm is particularly powerful in discriminating a pedestrian from a cluttered situation, where some background regions may appear to have human shapes, but their motion differs from human movement. Unlike the algorithm based on a co-occurrence feature descriptor where significant generalization errors may arise owing to the lack of extensive training samples to cover feature variations, the proposed algorithm describes the shape and motion as unique features. These features enable us to train a pedestrian detector in the form of a spatio-temporal histogram of oriented gradients using the AdaBoost algorithm with a relatively small training dataset, while still achieving excellent detection performance. We have confirmed the effectiveness of the proposed algorithm through experiments on several public datasets.

Face detection has been an independent technology playing an important role in more and more fields, which makes it necessary and urgent to have its architecture reconfigurable to meet different demands on detection capabilities. This paper proposed a face detection architecture, which could be adjusted by the user according to the background, the sensor resolution, the detection accuracy and speed in different situations. This user adjustable mode makes the reconfiguration simple and efficient, and is especially suitable for portable mobile terminals whose working condition often changes frequently. In addition, this architecture could work as an accelerator to constitute a larger and more powerful system integrated with other functional modules. Experimental results show that the reconfiguration of the architecture is very reasonable in face detection and synthesized report also indicates its advantage on little consumption of area and power.

This paper presents a commercial shot classification scheme combining well-designed visual and textual features to automatically detect TV commercials. To identify the inherent difference between commercials and general programs, a special mid-level textual descriptor is proposed, aiming to capture the spatio-temporal properties of the video texts typical of commercials. In addition, we introduce an ensemble-learning based combination method, named Co-AdaBoost, to interactively exploit the intrinsic relations between the visual and textual features employed.

In this letter, we present useful features accounting for pronunciation prominence and propose a classification technique for prominence detection. A set of phone-specific features are extracted based on a forced alignment of the test pronunciation provided by a speech recognition system. These features are then applied to the traditional classifiers such as the support vector machine (SVM), artificial neural network (ANN) and adaptive boosting (Adaboost) for detecting the place of prominence.

This paper describes a vision-based and real-time system for detecting road signs from within a moving vehicle. The system architecture which is proposed in this paper consists of two parts, the learning and the detection part of road sign images. The proposed system has the standard architecture with adaboost algorithm. Adaboost is a popular algorithm which used to detect an object in real time. To improve the detection rate of adaboost algorithm, this paper proposes a new combination method of classifiers in every stage. In the case of detecting road signs in real environment, it can be ambiguous to decide to which class input images belong. To overcome this problem, we propose a method that applies fuzzy measure and fuzzy integral which use the importance and the evaluated values of classifiers within one stage. It is called fuzzy-boosting in this paper. Also, to improve the speed of a road sign detection algorithm using adaboost at the detection step, we propose a method which chooses several candidates by using MC generator. In this paper, as the sub-windows of chosen candidates pass classifiers which are made from fuzzy-boosting, we decide whether a road sign is detected or not. Using experiment result, we analyze and compare the detection speed and the classification error rate of the proposed algorithm applied to various environment and condition.

We have previously proposed a noise-robust speaker verification method using fundamental frequency (F0) extracted using the Hough transform. The method also incorporates an automatic stream-weight and decision threshold estimation technique. It has been confirmed that the proposed method is effective for white noise at various SNR conditions. This paper evaluates the proposed method in more practical in-car and elevator-hall noise conditions. The paper first describes the noise-robust F0 extraction method and details of our robust speaker verification method using multi-stream HMMs for integrating the extracted F0 and cepstral features. Details of the automatic stream-weight and threshold estimation method for multi-stream speaker verification framework are also explained. This method simultaneously optimizes stream-weights and a decision threshold by combining the linear discriminant analysis (LDA) and the Adaboost technique. Experiments were conducted using Japanese connected digit speech contaminated by white, in-car, or elevator-hall noise at various SNRs. Experimental results show that the F0 features improve the verification performance in various noisy environments, and that our stream-weight and threshold optimization method effectively estimates control parameters so that FARs and FRRs are adjusted to achieve equal error rates (EERs) under various noisy conditions.

A multi-stage approach -- which is fast, robust and easy to train -- for a face-detection system is proposed. Motivated by the work of Viola and Jones [1], this approach uses a cascade of classifiers to yield a coarse-to-fine strategy to reduce significantly detection time while maintaining a high detection rate. However, it is distinguished from previous work by two features. First, a new stage has been added to detect face candidate regions more quickly by using a larger window size and larger moving step size. Second, support vector machine (SVM) classifiers are used instead of AdaBoost classifiers in the last stage, and Haar wavelet features selected by the previous stage are reused for the SVM classifiers robustly and efficiently. By combining AdaBoost and SVM classifiers, the final system can achieve both fast and robust detection because most non-face patterns are rejected quickly in earlier layers, while only a small number of promising face patterns are classified robustly in later layers. The proposed multi-stage-based system has been shown to run faster than the original AdaBoost-based system while maintaining comparable accuracy.

Active Shape Model (ASM) has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. ASM local appearance model parameter estimation is based on the assumption that residuals between model fit and data have a Gaussian distribution. Moreover, to generate an allowable face shape, ASM truncates coefficients of shape principal components into the bounds determined by eigenvalues. In this paper, an algorithm of modeling local appearances, called AdaBoosted ASM, and a shape parameter optimization method are proposed. In the algorithm of modeling the local appearances, we describe our novel modeling method by using AdaBoosted histogram classifiers, in which the assumption of the Gaussian distribution is not necessary. In the shape parameter optimization, we describe that there is an inadequacy on controlling shape parameters in ASM, and our novel method on how to solve it. Experimental results demonstrate that the AdaBoosted histogram classifiers improve robustness of landmark displacement greatly, and the shape parameter optimization solves the inadequacy problem of ASM on shape constraint effectively.

This paper describes a pattern classifier for detecting frontal-view faces via learning a decision boundary. The proposed classifier consists of two major parts for improving classification accuracy: the implicit modeling of both the face and the near-face classes resulting in an extended discriminative feature set, and the subsequent composite Support Vector Machines (SVMs) for speeding up the classification. For the extended discriminative feature set, Principal Component Analysis (PCA) or Independent Component Analysis (ICA) is performed for the face and near-face classes separately. The projections and distances to the two different subspaces are complementary, which significantly enhances classification accuracy of SVM. Multiple nonlinear SVMs are trained for the local facial feature spaces considering the general multi-modal characteristic of the face space. Each component SVM has a simpler boundary than that of a single SVM for the whole face space. The most appropriate component SVM is selected by a gating mechanism based on clustering. The classification by utilizing one of the multiple SVMs guarantees good generalization performance and speeds up face detection. The proposed classifier is finally implemented to work in real-time by cascading a boosting based face detector.