We propose a new hybrid image compression algorithm which combines the F-transform and the JPEG. At first, we apply the direct F-transform and then, the JPEG compression. Conversly, the JPEG decompression is followed ...
详细信息
ISBN:
(纸本)9781509060344
We propose a new hybrid image compression algorithm which combines the F-transform and the JPEG. At first, we apply the direct F-transform and then, the JPEG compression. Conversly, the JPEG decompression is followed by the inverse F-transform to obtain the decompressed image. This scheme brings three benefits: (i) the direct F-transform filters out high frequencies so that the JPEG can reach a higher compression ratio;(ii) the JPEG color quantization can be omitted in order to achieve greater decompressed image quality;(iii) the JPEG-decompressed image is processed by by the inverse F-transform w.r.t. the adjoint partition almost lossless. The paper justifies the proposed hybrid algorithm by benchmarks which show that the hybrid algorithm achieves significantly higher decompressed image quality than the JPEG.
While the popularity of high-resolution, computer-vision applications (e.g. mixed reality, autonomous vehicles) is increasing, there have been complementary advances in time-of-flight depth sensor resolution and quali...
详细信息
ISBN:
(纸本)9781728102481;9781728102474
While the popularity of high-resolution, computer-vision applications (e.g. mixed reality, autonomous vehicles) is increasing, there have been complementary advances in time-of-flight depth sensor resolution and quality. These advances in time-of-flight sensors provide a platform for new research into real-time, depth-upsampling algorithms targeted at high-resolution video systems with low-latency requirements. This paper describes a case study in which a previously developed bilateral-filter-style upsampling algorithm is profiled, parallelized, and accelerated on an FPGA using high-level synthesis tools from Xilinx. We show that our accelerated algorithm can effectively upsample the resolution and reduce the noise of time-of-flight sensors. We also demonstrate that this algorithm exceeds the real-time requirements of 90 frames per second necessitated by mixed-reality hardware, achieving a lower-bound speedup of 40 times over the fastest CPU-only version.
Over the last 20 years, several crack detection algorithms have been developed to implement safe and efficient automated road condition survey (ARCS) systems. Although the current state-of-the-art algorithms can achie...
详细信息
Over the last 20 years, several crack detection algorithms have been developed to implement safe and efficient automated road condition survey (ARCS) systems. Although the current state-of-the-art algorithms can achieve a high level of accuracy, their computation time makes them infeasible to implement in real-time without massive parallelization. This paper presents a fast and accurate crack detection algorithm. The algorithm consists of the following major steps: 1) image preprocessing;2) Preliminary crack segmentation to minimize false negatives;3) Crack object generation and connection to remove false positives;and 4) Refinement of the crack segmentation through a minimal path search based procedure. The proposed algorithm achieves an overall score of 80 in the Crack Detection Algorithm Performance Evaluation System (CDA-PES). With a median processing time of 0.52 seconds for 0.65 megapixel images on a single CPU thread, this algorithm makes accurate, real-time processing viable. The research presented in this paper contributes towards more widespread adoption of safer and efficient automated road condition surveys.
A method designed to reconstruct outdoor 3D building models automatically from a point cloud is presented in this paper. The proposed approach starts with building detection using spectral and spatial data from the UA...
详细信息
ISBN:
(纸本)9781728102481;9781728102474
A method designed to reconstruct outdoor 3D building models automatically from a point cloud is presented in this paper. The proposed approach starts with building detection using spectral and spatial data from the UAV point cloud to remove non-building features. RANSAC, modified convex hull, and line growing algorithms are used to extract main roof planes and their boundaries. Roof planes are adjusted to each other using geometrical constraints, the height of each plane is estimated and a 3D model for the whole structure is constructed with LoD2. The key contribution of this approach is using a hybrid approach of model-driven with statistical analysis for modeling complex structures from a noisy point cloud. The reconstructed model shows that the workflow is sufficient to describe the whole building structure in the required LoD.
The book is a collection of high-quality peer-reviewed research papers presented at International conference on Information System Design and Intelligent Applications (INDIA 2017) held at Duy Tan University, Da Nang, ...
ISBN:
(数字)9789811075124
ISBN:
(纸本)9789811075117
The book is a collection of high-quality peer-reviewed research papers presented at International conference on Information System Design and Intelligent Applications (INDIA 2017) held at Duy Tan University, Da Nang, Vietnam during 15-17 June 2017. The book covers a wide range of topics of computer science and information technology discipline ranging from imageprocessing, database application, data mining, grid and cloud computing, bioinformatics and many others. The various intelligent tools like swarm intelligence, artificial intelligence, evolutionary algorithms, bio-inspired algorithms have been well applied in different domains for solving various challenging problems.
In fisheries industry, flatfish accounts for about half of the domestic fish production and is a specie with active aquaculture activities. As flatfish grows, classification according to the size should be periodicall...
详细信息
ISBN:
(纸本)9781538670804;9788993215168
In fisheries industry, flatfish accounts for about half of the domestic fish production and is a specie with active aquaculture activities. As flatfish grows, classification according to the size should be periodically carried out for efficient growth. In this paper, the correlation between area and weight of flatfish required for classification algorithms using machine vision is derived. 120 simulations are performed using flatfish models and the area is obtained through imageprocessing. In imageprocessing process, the area of flatfish model is calculated using a reference square known in size. The weight of actual fish corresponding to the length of the model is obtained using the reference equation. Then, regression analysis is performed to derive the interpolation of linear and power equations which show correlation between area and weight of the flatfish.
image registration is a common task for many biomedical analysis applications. The present work focuses on the benchmarking of registration methods on differently stained histological slides. This is a challenging tas...
详细信息
image registration is a common task for many biomedical analysis applications. The present work focuses on the benchmarking of registration methods on differently stained histological slides. This is a challenging task due to the differences in the appearance model, the repetitive texture of the details and the large image size, between other issues. Our benchmarking data is composed of 616 image pairs at two different scales — average image diagonal 2.4k and 5k pixels. We compare eleven fully automatic registration methods covering the widely used similarity measures (and optimization strategies with both linear and elastic transformation). For each method, the best parameter configuration is found and subsequently applied to all the image pairs. The performance of the algorithms is evaluated from several perspectives — the registrations (in) accuracy on manually annotated landmarks, the method robustness and its processing computation time.
This paper presents the implementation of Particle filter based Object tracking using ReconOS on Reconfigurable Computing System. Multithreading can be used to improve the performance of complex imageprocessing algor...
详细信息
This paper presents the implementation of Particle filter based Object tracking using ReconOS on Reconfigurable Computing System. Multithreading can be used to improve the performance of complex imageprocessingalgorithms, but their sequential execution is a barrier which can be tackled by the effective use of FPGAs. In order to accomplish the desired performance, an operating system, ReconOS is used on an ARM based CPU-FPGA hybrid platform. ReconOS extends communication and synchronization primitives of operating systems like mutexes, semaphores, condition variable and message boxes to reconfigurable hardware. ReconOS provides the advantage of mapping the particle filter algorithm into reconfigurable hardware and accessing the data from software threads. Thus providing improved performance, portability and unified appearance as well as transparency to the object tracking application.
With the rapid development of multimedia applications which involves images, video and audio, security has become an important aspect of modern day digital communication. Various fields like multimedia systems, teleme...
详细信息
With the rapid development of multimedia applications which involves images, video and audio, security has become an important aspect of modern day digital communication. Various fields like multimedia systems, telemedicine, military communications, medical imaging internet communications etc, are widely based on image security. Our focus in this paper is to propose an algorithm which enhances image security. The algorithm proposed provides two-level security for the images that are transmitted over networks. We are using an existing and novel Data Mining technique, called Closed Frequent Itemset Mining to encode the image. Upon this, we are applying an image security technique called Steganography to hide the very existence of the image whilst being sent. With this higher security levels, an image can be sent securely over any network with the image's existence completely hidden. Two prominent quality metrics are tested: They are Mean Square Error (MSE) and Peak Signal to Noise Ratio (PSNR). Mean Square Error has been reduced efficiently and Peak Signal to Noise Ratio showed much improvement, which proves that the algorithm not only provides multi-layer security but also preserves the quality of images. The effect of Minimum Support Count and message image size on PSNR has also been observed. Also, their effect on time taken by the algorithm has been observed and plotted.
Fuzzy C-Means and Possibilistic C-Means are two most used algorithms in the computer aided diagnosis systems-(CAD) for image segmentation. Due to simple implementation, fast convergence and unsupervised procedure, the...
详细信息
ISBN:
(纸本)9781538644058
Fuzzy C-Means and Possibilistic C-Means are two most used algorithms in the computer aided diagnosis systems-(CAD) for image segmentation. Due to simple implementation, fast convergence and unsupervised procedure, these algorithms have been become widespread and the most desirable methods to employ in disparate image segmentation problems. However, emerging new imaging devices and different quality of images, unveil disability of these methods. Falling in local optima and high sensitivity to noise and outliers, have confronted the scholars with the new challenges in recent decades. This paper by employing a meta-heuristic algorithm, Differential Evolution, and kernel-based inner product norm metric has taken a new direction yet simple to overcome to initial configuration sensitivity and premature convergence in the conventional FCM and PCM. Proposed method succeeded to get to an accuracy about 94% true segmentation of brain tissue in presence of noise and intensity inhomogeneity.
暂无评论