The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In both human and machine vision systems, edges in images are of crucial significance in understanding the contents of images. Edge detection has therefore become an important task in image processing. In this paper, we propose a new operator for detecting edges in images. This operator is based on the principle of evaluating the local fluctuation of the pixel values. We first normalize the pixel...
Medulloblastoma (MB) is the most common brain tumor in children. Recent studies have demonstrated a relationship between specific signaling pathway abnormalities, a tendency to more favorable outcomes, and a histopathological feature: nodular growth patterns. In this work we present a new segmentation scheme which requires minimal user interaction to segment nodules on MB histopathological sections...
Colour regards urban landscape of important elements, it can reflect a city's history, local features and cultural tradition. This paper discusses to colour aesthetic application in urban landscape design, namely how to play a landscape of natural colour and artificial colour features and create urban landscape beauty of colours.
Scene classification from images is a challenging problem in computer vision due to its significant variability of scale, illumination, and view. Recently, Latent Dirichlet Allocation (LDA) model has grown popular in computer vision field, especially in scene labeling and classification. However, the effectiveness of the LDA model for the scene classification has not yet been addressed thoroughly...
Image identification of plant leaves based on human vision is difficult task as well as plant identification based on keywords retrieval. It requires the domain knowledge in the botanist field. This work proposes the image texture analysis using Discrete Wavelet Transformation (DWT) and combined with an entropy measurement to identify a query image to one of seven classes that consists of 280 plant...
Color image demosaicking aims to reconstruct the full-resolution RGB image from a mosaicked Color Filter Array (CFA) image. Instead of reconstructing the red, green, and blue color channels separately, most demosaicking approaches mutually recover them. However, CFA images tend to be distorted by the non-ideal response of the camera sensor, and possible motion or out-of-focus blurs during the acquisition...
Through researched the method of the identification and location based on machine vision, location information of mature tomatoes has been obtained, which can be used to guide the automated picking operation of ripe tomatoes. The segmentation of visual system is based on the difference between the color characteristics of ripe tomatoes and background. Through the gray-scale method, the treatment of...
Summary form only given. We present efficient machine learning methods for color image compression which simultaneously learn bases for compact image representation as well as the color space. We show the benefits of representing color image patches as 2D matrices of size n × 3n rather than as 3D patches of size n × n × 3. We also present a method to leverage greater representational power from a...
Combining the intelligent algorithm such as BP neural network and support vector maching (SVM) with traditional chemical method, this paper models the relationship between plant surface color and its pigment. Using the neural network model constructed above, people can figure out the content of plant pigments by getting the corresponding plant surface color information. Compared with the traditional...
Grabcut is an Interactive segmentation algorithm, which is employed to extract the foreground of an image, but it works wrong frequently when the pixels around the foreground are similar to the pixels of the background. We advance a new cost function to correct the mistake after we analyze the reason why it works wrong. Experimental results show that the new cost function outperforms the original...
This work describes a method for accurately tracking persons in indoor surveillance video stream obtained from a static camera with difficult scene properties including illumination changes and solves the major occlusion problem. First, moving objects are precisely extracted by determining its motion, for further processing. The scene illumination changes are averaged to obtain the accurate moving...
Real-time object tracking is recently becoming more and more important in the field of video analysis and processing. Applications like traffic-control, user-computer interaction, online video processing and production and video surveillance need reliable and economically affordable video tracking tools. This paper presents a new method for object tracking with improved efficiency by reducing the...
Summarized the vision structure frame of the YSU soccer robot system and detailedly introduced the key technique of the visual system. Through geometric correction, it settled the problem of image deformation existing in imaging system itself. In order to improve image processing speed and precision, proposed the HSV color space model to process image, after analyzing the RGB color space model advantage...
Recently, there are many autonomous navigation applications done in outdoor environment. However, safe navigation is still a daunting challenge in terrain containing vegetation. Thus, a study on vegetation detection for outdoor automobile navigation is investigated in this work. At the early state of our research, we focused on the segmentation of LADAR data into two classes by using local three-dimensional...
The soccer robot assembly system belongs to the intelligence robot assembly system, this article take the YSU soccer robot assembly system as a platform, proposed unifies the auto-adapted threshold value method based on HIS and RGB, improved in the original system in the multi-objective search process image to gather slow and the robust bad situation.
Human's safety in construction areas is vital. A hard hat is required to enter a construction area. Stopping a person who is not wearing a hard hat entering a construction area is very important. Video-based surveillance to detect hard hat is a new solution to this safety problem. This paper brings different video processing techniques together to construct a framework for fast and robust hard hat...
Image morphing has received much attention in recent years. It mainly involves feature specification, geometric transformation and color blending. Here, a novel calculation method of image morphing is proposed. First, a novel coordinate system called triangle coordinate system is defined, which has a great advantage in geometric transformation. Second, corresponding feature points on images are marked...
Background subtraction is a process of separating moving foreground objects from the non-moving background. This technique must adapt to the illumination, motion and the geometry background changes such as shadow, reflections, and etc. In this paper, one of the traditional background subtraction techniques which is frame differencing (FD) is conducted to detect the moving object in outdoor environment...
The objective is to develop a probabilistic approach for vision-based fire detection in videos. The proposed method analyzes the frame-to-frame changes of specific low-level features describing potential fire regions. These features are color, area size, surface coarseness, boundary roughness, and skewness within estimated fire regions. Because of flickering and random characteristics of fire, these...
Colour structured light with spatial neighbourhood is one of the famous techniques that are used to acquire 3D information. By projecting the pattern onto the targeted object and taking the image, the structured light is measured as coded words and the corresponding points could be found. Finally, the process to reconstruct 3D information could be solved using the principle of triangulation. A major...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.