To increase the efficiency of the laser coagulation surgery the problem of the most accurate segmentation of fundus images is especially relevant. Fundus image segmentation is carried out with high accuracy using effe...
详细信息
Regenerated tissue is a one of the wide developing research topics of nowadays. the characterization of tissue in culture permits to regulate its final mechanical properties and to test the influence of pharmaceutical...
详细信息
Regenerated tissue is a one of the wide developing research topics of nowadays. the characterization of tissue in culture permits to regulate its final mechanical properties and to test the influence of pharmaceutical and cosmetic products on it. For this purpose, an embedded vision system was developed in order to characterize the mechanical properties of tissue in culture. thus, the aim of the present study was to develop an embedded, automated and portable cell count algorithm which can quantify the fibroblast cells from the fluorescent images taken by developed FPGA driven embedded high definition (HD) camera module. the developed algorithm was integrated into "uCell" software and tested on fluorescent images. the automated cell counting results were compared with manual counting and showed that the algorithm is reliable in 95% percentage of cases. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
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.
Traffic Light detection and recognition has become one of the critical research areas when it comes to autonomous driving vehicles. Developing an algorithm to detect different shaped traffic lights such as traffic lig...
详细信息
ISBN:
(纸本)9781538673539;9781538673522
Traffic Light detection and recognition has become one of the critical research areas when it comes to autonomous driving vehicles. Developing an algorithm to detect different shaped traffic lights such as traffic lights (TLs) with arrowheads, circular shapes, horizontally and vertically oriented TLs and TLs in different illumination conditions during daytime still remains a challenge. this paper evaluates the existing algorithms, which uses heuristic or template matching based imageprocessing methods and other learning based systems, that consumes higher time and processing power for training and map based systems and proposes a novel optimized algorithm using machine vision techniques to meet those challenges. the experiments were carried out using videos taken by front camera of vehicles. the results of the algorithm show a higher accuracy for precision and recall evaluations.
Photoacoustic tomography is a quickly growing imaging method that can provide images of high spatial resolution and high contrast at a limited depths. Medical photoacoustic processing characteristics two main componen...
详细信息
ISBN:
(纸本)9781538650431;9781538662175
Photoacoustic tomography is a quickly growing imaging method that can provide images of high spatial resolution and high contrast at a limited depths. Medical photoacoustic processing characteristics two main components: A transducer is required to transmit laser pulses and acquire the reflected ultrasound signals and a back-end processing system that will generate the final reconstructed image. In this paper, we introduce an implementation of the receive part of proposed embedded system and briefly discuss reconstruction algorithms which are used in medical imaging systems. Furthermore, an intellectual property core (IP-core), which can be controlled and configured by a user application on Zynq-7000 System-On-Chip (SoC) via AXI-Lite Interface, that can receive multichannel digitized raw signals from Analog-Front-End (AFE) device via Low Voltage Differential Signal (LVDS), is proposed for photoacoustic imaging systems. Besides, block diagram of the system, the hardware design flow and the proposed IP-core are fully described in this paper. In order to effortlessly test and evaluate a wide variety of ultrasonic signal processing applications, 16 channel system is implemented and demonstrated by using TI AFE5816 Evaluation module (EVM) based on AFE5816 device and Xilinx ZC702 Evaluation Kit based on Zynq-7000 SoC. Apart from working on hardware, we review and commented on the proposed 3-Dimensional photoacoustic image reconstruction algorithm.
OCR (Optical Character Recognition) has been becoming a vital method to recognize digits, letters, symbols and so on. the main idea is basically the conversion of data files which consists of handwritten or machine-wr...
详细信息
ISBN:
(纸本)9781538670804;9788993215168
OCR (Optical Character Recognition) has been becoming a vital method to recognize digits, letters, symbols and so on. the main idea is basically the conversion of data files which consists of handwritten or machine-written digits or characters into a type to let the machine make edits and read. this way, it lets computers read articles or books. they can also read images and make the conversion to a text file by using OCR. there are two important benefits of OCR. First, is the enhancement of the device to operate more productively even if the number of employees is decreased. Secondly, is the increase in the efficiency of the storage. this paper compares two state-of-the-art OCR algorithms in a simulated environment by using modified dataset. Simulation results are shown in part 4.
the parallelization of programs and distributing their workloads to multiple threads can be a challenging task. In addition to multithreading, harnessing vector units in CPUs proves highly desirable. However, employin...
详细信息
ISBN:
(纸本)9781450350303
the parallelization of programs and distributing their workloads to multiple threads can be a challenging task. In addition to multithreading, harnessing vector units in CPUs proves highly desirable. However, employing vector units to speed up programs can be quite tedious. Either a program developer solely relies on the auto-vectorization capabilities of the compiler or he manually applies vector intrinsics, which is extremely error-prone, difficult to maintain, and not portable at all. Based on whole-function vectorization, a method to replace control flow with data flow, we propose auto-vectorization techniques for imageprocessing DSLs in the context of source-to-source compilation. the approach does not require the input to be available in SSA form. Moreover, we formulate constraints under which the vectorization analysis and code transformations may be greatly simplified in the context of imageprocessing DSLs. As part of our methodology, we present control flow to data flow transformation as a source-to-source translation. Moreover, we propose a method to efficiently analyze algorithms with mixed bit-width data types to determine the optimal SIMD width, independently of the target instruction set. the techniques are integrated into an open source DSL framework. Subsequently, the vectorization capabilities are compared to a variety of existing state-of-the-art C/C++ compilers. A geometric mean speedup of up to 3.14 is observed for benchmarks taken from ISPC and imageprocessing, compared to non-vectorized executions.
Lane detection and tracking is essential concern in vision based autonomous vehicle navigation. this paper proposes a novel method based on probabilistic Hough transform and motion vector based analysis for detecting ...
详细信息
ISBN:
(纸本)9781538673539;9781538673522
Lane detection and tracking is essential concern in vision based autonomous vehicle navigation. this paper proposes a novel method based on probabilistic Hough transform and motion vector based analysis for detecting and tracking lane and lane departures. It addresses drawbacks of current systems under hazy situations with learning method based on previous tracking records of the system. In this method relevant lane mark features are extracted based on color variations. therefore used HSL color model which gives higher color contrast of road surface and the markings. In order to reduce computation, processingalgorithms are applied only to the region of interest (ROI). Edges of the selected regions are extracted with Canny Edge Detection. Since lane markings are made with set of straight lines, straight lines are extracted with Probabilistic Hough Transform. Extracted lines are analyzed to detect lane. To monitor lane departures vehicle's motion is detected and tracked based on motion vector analysis with Lucas Kanade Optical Flow algorithm. Previous detection records are used to track the lane continuously in hazy situations and provide prediction on approximate lane for the roads without lane markings. Experiments were performed on set of videos taken from vehicles' front camera mounted on dashboard. According to the experiments the proposed algorithm has 81.9% of sensitivity in lane detection and 63.5% in approximate lane predictions for the roads without lane markings. Lane detection algorithm has 83% precision, 68% recall and 0.75 F1 score withthreshold brightness value 140. Algorithm can further improved to guide the autonomous vehicles to take accurate decisions on selecting safety lane to drive ahead in different situations.
In the field of aircraft design, the last few decades have focused on the iterative improvement of conventional tube-and-wing designs to reduce cost, noise, and emission. Nevertheless, the growing expectation in terms...
详细信息
A map of a location made of a human mindset is made briefly by recording a situation already seen in memory. Human behavior is easy to do without a lot of thinking. the process is observed more deeply that when the hu...
详细信息
暂无评论