Abstract:This work presents a binarization technique of map document images. It exploits an amalgam of global and local threshold approaches best suited for binarization of document images with complex background and overlapping objects in the foreground like maps. The proposed approach uses Distance Transform (DT) and Adaptive threshold. Initially a rough estimate of the map background is done using Distance Transform (DT). This is followed by an adaptive threshold operation to extract the foreground. The efficacy and… Show more
“…Because disturbances can also be induced by the different microfluidic environments, the micro-robot can deviate easily from the desired route, and scratch or even collide with the blood vessel wall, which would cause unpredictabilities in the motion state. Therefore, we tried to set a safe and stable path for the micro-robot away from the vessel wall along the central line of the microfluidic environment, where the blood has steady flow velocity, as shown in Figure 1B (Zhang, 2008 ; Qi and Xu, 2010 ; Biswas et al, 2014 ; Shi and Long, 2014 ; Deng and Huang, 2017 ; Jiang et al, 2020 ). The skeleton of the vessel-mimic map was extracted, with which we could obtain the center line of the passable area through refinement iteration.…”
Manipulating micro-robots in blood vessels is an essential technology for medical researchers in applications such as drug delivery and thrombus removal. The usage of micro-robots in medicine can help overcome the limitations of many conventional clinical methods. In this study, we aimed to make the micro-robot more intelligent while moving through blood vessels. First, the skeleton of an image of the blood vessels is extracted, which is further used for path planning. Then, the skeleton-extraction-based A* algorithm was used for determining a best route for the movement of the microrobot at a safe distance from the vascular wall. Finally, the gradient descent algorithm was utilized to smooth the planned path. Simulations were conducted to verify the effectiveness of the proposed algorithms. The proposed methods would improve the efficiency for the further manipulation of the micro-robot in the blood vessel environment.
“…Because disturbances can also be induced by the different microfluidic environments, the micro-robot can deviate easily from the desired route, and scratch or even collide with the blood vessel wall, which would cause unpredictabilities in the motion state. Therefore, we tried to set a safe and stable path for the micro-robot away from the vessel wall along the central line of the microfluidic environment, where the blood has steady flow velocity, as shown in Figure 1B (Zhang, 2008 ; Qi and Xu, 2010 ; Biswas et al, 2014 ; Shi and Long, 2014 ; Deng and Huang, 2017 ; Jiang et al, 2020 ). The skeleton of the vessel-mimic map was extracted, with which we could obtain the center line of the passable area through refinement iteration.…”
Manipulating micro-robots in blood vessels is an essential technology for medical researchers in applications such as drug delivery and thrombus removal. The usage of micro-robots in medicine can help overcome the limitations of many conventional clinical methods. In this study, we aimed to make the micro-robot more intelligent while moving through blood vessels. First, the skeleton of an image of the blood vessels is extracted, which is further used for path planning. Then, the skeleton-extraction-based A* algorithm was used for determining a best route for the movement of the microrobot at a safe distance from the vascular wall. Finally, the gradient descent algorithm was utilized to smooth the planned path. Simulations were conducted to verify the effectiveness of the proposed algorithms. The proposed methods would improve the efficiency for the further manipulation of the micro-robot in the blood vessel environment.
“…Pixel-level text segmentation There is a long history of text segmentation [13] and image binarization [14][15] [16] [17] in the document analysis community related to historical manuscripts [18], maps [19], handwritten text [20], documents [21] and more. One of such works that does pixel level segmentation of text in document images is BCDU-net [22].…”
The detection and recognition of unconstrained text is an open problem in research. Text in comic books has unusual styles that raise many challenges for text detection. This work aims to binarize text in a comic genre with highly sophisticated text styles: Japanese manga. To overcome the lack of a manga dataset with text annotations at a pixel level, we create our own. To improve the evaluation and search of an optimal model, in addition to standard metrics in binarization, we implement other special metrics. Using these resources, we designed and evaluated a deep network model, outperforming current methods for text binarization in manga in most metrics.
“…The scanned gray image (I gr ) is first converted to binary image, (I bw ) by using the method in [4] and then thinned to get I th ; the input image used in our work. I th consists of some set of stroke points which are considered https://code.google.com/p/lmidb/…”
Text segmentation from land map images is a non-trivial task as map components are interleaved and overlapped in a complex spatial form. The characters in a word in most of the Indic languages, including Bangla (the 6th most spoken language in the world), are connected through a headline (”matra” or ”shirorekha”) which makes the corresponding word a single component. It has been observed that the Delaunay triangulation (DT) forms a number of small triangles on the text regions compared to other regions of the map - a property very much discernible for Bangla (and some other Indic scripts) texts. This property is primarily exploited here to segment text from the complex background of the land map images. The proposed text segmentation approach is tested and compared with an existing method on a collected dataset of paper map images( containing Bangla, an Indian regional language texts) and the results are encouraging.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.