Fig 2 - uploaded by Hooman Samani
Content may be subject to copyright.
Source publication
As time goes by, our technology gets improve day by day. We can know that it gets better in robotic technology. Robots try to social with human beings immediately. For the input, image processing becomes more important because it can make sure the human's actions and reactions. It is unavoidable that get some noise when the camera takes photo as in...
Citations
... Noisy image and noise removal image by median filte[17] ...
Acknowledgments I extend my heartfelt appreciation to CETIC for providing me with an invaluable opportunity to contribute to the dynamic field of medical imaging during my internship. I express my sincere gratitude to Mr. Xavier Lessage and Mr. Leandro Collier for their unwavering support, expert guidance, and encouragement throughout this enriching experience. I would also like to acknowledge the entire team at CETIC for fostering a welcoming and supportive environment. This specific experience has not only allowed me to develop new skills but also provided me with valuable insights into advancing healthcare technology. This internship has been a cornerstone in my professional development , and I am deeply grateful to everyone at CETIC who contributed to its success. Abstract Artificial intelligence (AI) is a transformative force that is reshaping various aspects of the world. Its applications span automation, person-alized services, predictive analytics, and enhanced decision-making. One of the notable contributions of AI in healthcare is its impact on diagnosis and treatment. Medical professionals are leveraging AI technologies to enhance diagnostic accuracy, leading to more precise and timely identification of various medical conditions. However, a significant limitation arises, in this field, from the scarcity or inadequacy of data. Privacy concerns often restrict the availability of large, diverse medical datasets, hindering the development of ML models. Additionally, rare diseases or specific medical conditions may not have sufficient data for effective model training. As a result, ML models may struggle to perform reliably across different scenarios. These limitations can lead to inaccuracies and overfitting, where models may not generalize well to diverse cases. Generative AI, including methods like Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs), offers a solution by synthesizing realistic medical data. Also, Stable diffusion is an outstanding diffusion model that paves the way for producing high-resolution images with thorough details from text prompts or reference images. Trained on existing datasets, these generative models can create artificial images that capture the complexities of various diseases and conditions. This augmentation process helps mitigate the limitations of small or unrepresentative datasets, enhancing model generalization and reducing the risk of overfitting. By introducing diverse and realistic synthetic data, generative AI contributes to the development of more robust ML models in medical imaging and diagnostics. It enables researchers and practitioners to train models on a broader range of scenarios, improving their accuracy and performance across different patient populations and conditions .
... Additionally, the training and inference processes are much faster than those of the detection algorithm based on candidate boxes and can meet the requirements for timeliness. However, there is still a certain gap in the accuracy between YOLO-v2 and the detection method based on the candidate frame [29], and this gap is usually considered to be caused by the category prediction and position regression in the subsequent convolutional layer and loss of high-resolution information. The target detection algorithm based on the candidate frames has more advantages in accuracy than the target detection algorithm based on direct regression, but its speed is slower. ...
Robot control based on visual information perception is a hot topic in the industrial robot domain and makes robots capable of doing more things in a complex environment. However, complex visual background in an industrial environment brings great difficulties in recognizing the target image, especially when a target is small or far from the sensor. Therefore, target recognition is the first problem that should be addressed in a visual servo system. This paper considers common complex constraints in industrial environments and proposes a You Only Look Once Version 2 Region of Interest (YOLO-v2-ROI) neural network image processing algorithm based on machine learning. The proposed algorithm combines the advantages of YOLO (You Only Look Once) rapid detection with effective identification of ROI (Region of Interest) pooling structure, which can quickly locate and identify different objects in different fields of view. This method can also lead the robot vision system to recognize and classify a target object automatically, improve robot vision system efficiency, avoid blind movement, and reduce the calculation load. The proposed algorithm is verified by experiments. The experimental result shows that the learning algorithm constructed in this paper has real-time image-detection speed and demonstrates strong adaptability and recognition ability when processing images with complex backgrounds, such as different backgrounds, lighting, or perspectives. In addition, this algorithm can also effectively identify and locate visual targets, which improves the environmental adaptability of a visual servo system
... We can remove noises by applying linear filters as Adaptive Filter and non-linear filters as Median filter or Wiener filter, but nonlinear filters are more effective (Hambal1, et al., 2015;Tien, et al., 2017). ...
Nowadays, image processing became very important especially in real-time where the results of real-time image processing failures can be severe; therefore, the study and research in methods of real-time image processing are of extreme significance. The main contribution of this paper is to provide an overview of the current state of real-time image processing research (Applications), the relevant techniques, and methods. Real-Time Image Processing; Methods of Image Processing; Techniques of Image Processing; Applications of Image Processing; Image Enhancement.
Vision relieves humans to understand the environmental deviations over a period. These deviations are seen by capturing the images. The digital image plays a dynamic role in everyday life. One of the processes of optimizing the details of an image whilst removing the random noise is image denoising. It is a well-explored research topic in the field of image processing. In the past, the progress made in image denoising has advanced from the improved modeling of digital images. Hence, the major challenges of the image process denoising algorithm is to advance the visual appearance whilst preserving the other details of the real image. Significant research today focuses on wavelet-based denoising methods. This research paper presents a new approach to understand the Sobel imaging process algorithm on the Linux platform and develop an effective algorithm by using different optimization techniques on SABRE i.MX_6. Our work concentrated more on the image process algorithm optimization. By using the OpenCV environment, this paper is intended to simulate a Salt and Pepper noisy phenomenon and remove the noisy pixels by using Median Filter Algorithm. The Sobel convolution method included and used in the design of a Sobel Filter and then process the image following the median filter, to achieve an effective edge detection result. Finally, this paper optimizes the algorithm on SABRE i.MX_6 Linux environment. By using algorithmic optimization (lower complexity algorithm in the mathematical sense, using appropriate data structures), optimization for RISC (loop unrolling) processors, including optimization for efficient use of hardware resources (access to data, cache management and multi-thread), this paper analyzed the different response parameters of the system with varied inputs, different compiler options (O1, O2, or O3), and different doping degrees. The proposed denoising algorithm shows Volume 7, Issue 6, November-December-2021 | http://ijsrcseit.com Waheed Muhammad SANYA et al Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol, November-December-2021, 7 (6) : 402-417 403 the meaningful addition of the visual quality of the images and the algorithmic optimization assessment.
In robot visual servoing system, effective detected the region of interest area (ROI) in target images is the first problem should be solved, but the detection is susceptible to an unstructured environment. In this paper, an instance segmentation network algorithm based on Mask Region Convolutional Neural Networks (Mask R-CNN) framework is proposed for ROI image preprocessing. As instance segmentation technology can distinguish complex environmental information, so first with this advantage filter out message such as shape or similar area to target image, then with semantic segmentation technology add special category labels to the filtered images and distinguish different individual instances in similar categories. Finally through the series steps aforementioned, robot vision system can overcome the impact of environmental factors and identify the target image. The proposed method is used to detect target image under five constraints such as occlusion and reflection, result shows the algorithm can effectively deal with challenges that brought by complex constraints, and even can predict the location data of missing information based on some image information. In addition, based on the algorithm proposed in this paper, we used one seven axis robot visual servo platform, executed visual servoing experiment under different unstructured environments, further verifies the effectiveness of our proposed method.
