Photometric stereo is a method to obtain surface normals of an object using its images captured under varying illumination directions. The existing deep learning-based methods require multiple images of an object capt...
详细信息
ISBN:
(纸本)9781665405409
Photometric stereo is a method to obtain surface normals of an object using its images captured under varying illumination directions. The existing deep learning-based methods require multiple images of an object captured using complex image acquisition systems. In this work, we propose a deep learning framework to perform three tasks jointly: (i) lighting estimation, (ii) image relighting, and (iii) surface normal estimation, all from a single input image of an object with non-Lambertian surface and general reflectance. The network explicitly segregates global geometric features and local lighting-specific features of the object from a single image. The local features resemble attached shadows, shadings, and specular highlights, providing valuable lighting estimation and relighting cues. The global features capture the lighting-independent geometric attributes that effectively guide the surface normal estimation. The joint training transfers valuable insights to achieve significant improvements across all three tasks. We show that the proposed single-image-based relighting framework outperforms several existing photometric stereo methods which require multiple images of a static object.
This paper presents an innovative way of image compression using Field-Programmable Gate Array (FPGA) implementation of the Integer Wavelet Transform (IWT) and Discrete Wavelet Transform (DWT) algorithms. For situatio...
详细信息
ISBN:
(数字)9798350384369
ISBN:
(纸本)9798350384376
This paper presents an innovative way of image compression using Field-Programmable Gate Array (FPGA) implementation of the Integer Wavelet Transform (IWT) and Discrete Wavelet Transform (DWT) algorithms. For situations where resources are limited, the flexibility and adaptability offered by the FPGA architecture are ideal. Our technique strikes a compromise between compression effectiveness and image quality by utilizing DWT for multi-resolution analysis and IWT for spatial redundancy reduction. Real-time processing and resource optimization are ensured by the FPGA implementation. FPGA-optimized algorithms that tackle resource constraints are among the contributions. Evaluations demonstrate enhanced signal-to-noise ratios, compression ratios, and execution times. This study highlights how fast FPGA can compress images, especially for embedded systems and space missions. The study not only improves image compression but also highlights how FPGA can be used to increase the effectiveness of signal processingalgorithms.
Bangladesh having a growing agricultural economy quick detection of plant leaf diseases is a primary requirement. Disease discovery with the existing diagnostic procedures demands a longer time. Therefore, growers fre...
详细信息
ISBN:
(纸本)9789811628771;9789811628764
Bangladesh having a growing agricultural economy quick detection of plant leaf diseases is a primary requirement. Disease discovery with the existing diagnostic procedures demands a longer time. Therefore, growers frequently miss the best time for stopping and treating diseases. Further, early identification and classification of pumpkin leaf diseases extremely needed. This paper proposes to discover the pumpkin leaf diseases by utilizing a modern imageprocessing procedure convolutional neural network (CNN). CNN applied for image classification and recognition because of its high accuracy. Besides, a comparison of traditional machine learning algorithms like support vector machines (SVM), K-nearest neighbor (KNN), decision tree, and Naive Bayes with the performance of CNN is demonstrated in our work. Tensorflow library was adopted to implement the CNN algorithm and Scikit-learn used in terms of utilizing the above-mentioned traditional machine learning algorithms. Finally, we detected the pumpkin leaf diseases by the algorithm that exhibits an assuring accuracy to our suggested approach.
The considerable body of data available for evaluating biometric recognition systems in Research and Development (R&D) environments has contributed to the increasingly common problem of target performance mismatch...
详细信息
ISBN:
(纸本)9798350364132;9798350364149
The considerable body of data available for evaluating biometric recognition systems in Research and Development (R&D) environments has contributed to the increasingly common problem of target performance mismatch. Biometric algorithms are frequently tested against data that may not reflect the real world applications they target. From a Testing and Evaluation (T&E) standpoint, this domain mismatch causes difficulty assessing when improvements in State-of-the-Art (SOTA) research actually translate to improved applied outcomes. This problem can be addressed with thoughtful preparation of data and experimental methods to reflect specific use-cases and scenarios. To that end, this paper evaluates research solutions for identifying individuals at ranges and altitudes, which could support various application areas such as counterterrorism, protection of critical infrastructure facilities, military force protection, and border security. We address challenges including image quality issues and reliance on face recognition as the sole biometric modality. By fusing face and body features, we propose developing robust biometric systems for effective long-range identification from both the ground and steep pitch angles. Preliminary results show promising progress in whole-body recognition. This paper presents these early findings and discusses potential future directions for advancing long-range biometric identification systems based on mission-driven metrics.
The use of machine learning (ML) in the medical field is hindered by the scarcity of high-quality data. This work tackles the deficiency of echocardiogram pictures (echoCG) by using advanced generative models for synt...
详细信息
The Valluvan app is a language solution for native Tamil speakers. The system emphasizes the recognition of name boards, translation, and speech output to enhance communication and access to information. The app utili...
详细信息
The yield estimation task altogether relies upon the way toward identifying and checking the quantity of fruits on trees. In production of fruit, basic yield the board choices are guided through the bloom frequency, i...
详细信息
image segmentation is one of the first steps in most imageprocessing procedures. The segmentation aims to obtain a more meaningful or simplified image representation by grouping pixels with common characteristics, wh...
详细信息
ISBN:
(纸本)9798350318876
image segmentation is one of the first steps in most imageprocessing procedures. The segmentation aims to obtain a more meaningful or simplified image representation by grouping pixels with common characteristics, which allows regions or features of interest to be uniquely identified. The result of the segmentation has a significant impact on the subsequent steps. Segmentation is part of several superior applications such as artificial vision, medical, topographic, and astronomical image analysis. No single or universal segmentation process gets optimal performance for all image types. Hence, determining a function that fits specific image types or applications becomes a detailed, complex, and not trivial task requiring much time and effort. In this paper, we propose using Multi-Objective Evolutionary algorithms (MOEAs) as a training tool that combines operations that represent the techniques and strategies commonly used for generating image segmentation. As a result, sequences of operations are suitable for specific applications or image types. The objective functions used to guide the evolutionary process are sensitivity maximization (TPR) and specificity maximization (TNR), the basic components of ROC analysis. Sensitivity and specificity are commonly used as classification metrics to evaluate the quality of a proposed segmentation compared to an ideal segmentation. We used sensitivity and specificity as objective functions rather than accuracy because, as stated in [1], the dependence on prevalence makes accuracy less effective than a simultaneous consideration of sensitivity and specificity. Experiments were conducted on multiple images that share common characteristics obtained from image databases, specifically: i) benign and malignant melanoma images, ii) ophthalmoscopic retinal images, and iii) binary cell form images, where the segmentation generated by the proposed algorithm was compared with ideal segmentation. The results are quite promising and show t
Machine learning techniques have made significant progress in recent years in the field of healthcare by assisting clinicians in treatment interventions, identification, detection along with the classification of a va...
详细信息
The identification of anomalies (such as bone fractures or tendonitis in muscles and soft tissues) through imageprocessing and analysis techniques in Computed Tomography (CT) images is today of great importance to as...
详细信息
ISBN:
(纸本)9789893334362
The identification of anomalies (such as bone fractures or tendonitis in muscles and soft tissues) through imageprocessing and analysis techniques in Computed Tomography (CT) images is today of great importance to assist doctors and health professionals in making accurate diagnoses. The extraction of relevant information from the CT image is characterized by the calculation of gray level input image attributes. Statistical moments (SM) are calculated using the gray level distribution of an image and are therefore generally calculated from that image's histogram. These characteristics provide a statistical description of the relationship between different gray levels in the CT image. Haralick proposed a methodology for describing textures based on second order statistics, where characteristics are derived from co-occurrence matrices, which are constructed by counting different combinations of gray levels in an image according to certain directions. In this work, it is intended to automatically identify and extract regions in CT images based on textures as an aid for a quick and accurate diagnosis. CT images are first pre-processed for noise reduction and image enhancement, followed by the application of Haralick textures to segment and detect zones of interest. Classifiers trained on the Haralick invariant features showed good accuracy and performance. Despite the presence of low contrast and noise in some images, the proposed algorithms present promising results in the segmentation and automatic identification of regions of tomographic images, being an important contribution to support health professionals in the characterization of anomalies and their extension. Good results are expected for the next step of this work in the detection and segmentation of anomalies in CT images.
暂无评论