Text Line Segmentation of Handwritten Documents by Area Mapping

Abhijeet Boragule,GueeSangLee 한국스마트미디어학회 2015 스마트미디어저널 Vol.4 No.3

Text line segmentation is a preprocessing step in OCR, which can significantly influence the accuracy of document analysis applications. This paper proposes a novel methodology for the text line segmentation of handwritten documents. First, the average width of the connected components is used to form a 1-D Gaussian kernel and a smoothing operation is then applied to the input binary image. The adaptive binarization of the smoothed image forms the final text lines. In this work, the segmentation method involves two stages: firstly, the large connected components are labelled as a unique text line using text line area mapping. Secondly, the final refinement of the segmentation is performed using the Euclidean distance between the text line and small connected components. The group of uniquely labelled text candidates achieves promising segmentation results. The proposed approach works well on Korean and English language handwritten documents captured using a camera.

Object Tracking with Sparse Representation based on HOG and LBP Features

Abhijeet Boragule,JungYeon Yeo,GueeSang Lee 한국콘텐츠학회 2015 International Journal of Contents Vol.11 No.3

Visual object tracking is a fundamental problem in the field of computer vision, as it needs a proper model to account for drastic appearance changes that are caused by shape, textural, and illumination variations. In this paper, we propose a feature-based visual-object-tracking method with a sparse representation. Generally, most appearance-based models use the gray-scale pixel values of the input image, but this might be insufficient for a description of the target object under a variety of conditions. To obtain the proper information regarding the target object, the following combination of features has been exploited as a corresponding representation: First, the features of the target templates are extracted by using the HOG (histogram of gradient) and LBPs (local binary patterns); secondly, a feature-based sparsity is attained by solving the minimization problems, whereby the target object is represented by the selection of the minimum reconstruction error. The strengths of both features are exploited to enhance the overall performance of the tracker; furthermore, the proposed method is integrated with the particle-filter framework and achieves a promising result in terms of challenging tracking videos.

FOMLC: Feature optimization and machine learning classification for malware detection

Abhijeet Thakare(아비짓 타카레),Euijong Lee(이의종),Young-Gab Kim(김영갑) 한국통신학회 2019 한국통신학회 학술대회논문집 Vol.2019 No.6

An Intelligent Docking Station Manager for Multiple Mobile Service Robots

Abhijeet Ravankar,Ankit A. Ravankar,Yukinori Kobayashi,Lv Jixin,Takanori Emaru,Yohei Hoshino 제어로봇시스템학회 2015 제어로봇시스템학회 국제학술대회 논문집 Vol.2015 No.10

Robot docking stations are of utmost important for service robots like security robots and automated guided vehicles in warehouses which are in continuous operation, and hence require frequent recharging. While a lot of research has been done on designing the actual hardware of the docking station itself, a practical situation of intelligently managing a limited number of docking stations in case of multiple robots has largely been ignored. We propose a docking station manager for multiple mobile service robots, which intelligently allots a mobile robot to the most appropriate docking station, based on the robot‘s task priority, location awareness of the robot and the docking station, power left in robot, and request order. We demonstrate, through experiments in real environment, that the proposed manager can function intelligently and resolve conflicts when the docking stations are fully occupied. We experimentally tested the proposed station manager in different conditions of varying task priorities, power levels, and emergency conditions of the robots, and found it to be robust to intelligently allocate the most appropriate robot with the appropriate charging dock.

Path Smoothing Extension for Various Robot Path Planners

Abhijeet Ravankar,Ankit A. Ravankar,Yukinori Kobayashi,Takanori Emaru 제어로봇시스템학회 2016 제어로봇시스템학회 국제학술대회 논문집 Vol.2016 No.10

Many path planning algorithms have previously been proposed for mobile robots to navigate from a start to a goal location in a given map. These planners generate a path which keeps a safe distance from the obstacles in the map. However, most of the global path planners generate a path with sharp and angular turns which is not desired for robot motion as robots must stop at these turns. A smooth path is desired for robot motion which allows the robot to move at nearly constant velocity. We present a novel path smoothing extension which uses the geometry of hypocycloids to smooth out the sharp and angular turns of the robot’s path and generates a smooth path for the robot to traverse. The proposed technique works as an ‘extension’ and can be used in conjunction with any of the previously proposed global path planners like D<SUP>*</SUP>, A<SUP>*</SUP>, Dijkstra, or PRM (Probabilistic Roadmap) planners. The proposed extension also generates ‘nodes’ on the robot’s path which can be used as points of retreat for the robot to avoid collision with other robots. Unlike other path smoothing algorithms which generates a wavy path for the robot and brings them close to the walls, the proposed path smoothing extension keeps straight paths of the robot straight, and smooths only the turns. We discuss the results in both simulated and real environments about the smooth paths generated by the proposed extension with different global path planners along with multirobot collision avoidance.

Screening for diabetes mellitus using gingival crevicular blood with the help of a selfmonitoring device

Subodh Gaikwad,Varsha Jadhav,Abhijit Gurav,Abhijeet R Shete,Abhijeet R Shete,Hitesh M Dearda 대한치주과학회 2013 Journal of Periodontal & Implant Science Vol.43 No.1

Purpose: The purpose of study was to compare blood glucose in capillary finger-prick blood and gingival crevice blood usinga self-monitoring blood glucose device among patients with gingivitis or periodontitis. Methods: Thirty patients with gingivitis or periodontitis and bleeding on probing (BOP) were chosen. The following clinicalperiodontal parameters were noted: probing depth, BOP, gingival bleeding index, and periodontal disease index. Blood sampleswere collected from gingival crevicular blood (GCB) and capillary finger-prick blood (CFB). These samples were analyzedusing a glucose self-monitoring device. Results: Descriptive statistical analysis has been carried out in the present study. Data were analyzed using a Pearson’s correlationcoefficient and Student’s t-test. A r-value of 0.97 shows very strong correlation between CFB and GCB, which was statisticallyhighly significant (P<0.0001). Conclusions: The authors conclude that GCB may serve as potential source of screening blood glucose during routine periodontalexamination in populations with an unknown history of diabetes mellitus.

First Impression Modelling and Prediction Using Vision Modality

Hamna Akram,Abhijeet Boragule,Zafran Khan,Moongu Jeon 한국정보과학회 2021 한국정보과학회 학술발표논문집 Vol.2021 No.12

Increase in stress on infrastructure facilities due to natural disasters

Juyeong Choi,Abhijeet Deshmukh,Makarand Hastak 서울시립대학교 도시과학연구원 2016 도시과학국제저널 Vol.20 No.2

The services of infrastructure are often compromised in a postdisaster situation. This could be due to a direct physical impact on the infrastructure or due to a cascading impact resulting from reduced services of the supporting infrastructure. The reduced infrastructure services are unable to adequately meet the postdisaster community needs. Therefore, infrastructure facilities are likely to be operated with high stress on their capacities above the allowable stress (i.e. designed capacities) for meeting the services required. The system is unable to sustain the required serviceability level without the infusion of additional capacities when the stress level exceeds the limit stress. For example, after Haiti’s devastating earthquake, disrupted utility services, limited road networks, and the lack of civic governance influenced the capacity of all essential service providers. Furthermore, the earthquake-impacted hospitals had limited resources such as patient beds, medical staff, medical supplies and equipment for meeting the increased health needs of the community. As a result, the hospital experienced increased levels of stress related to services as they were unable to adequately meet the community health needs without external assistance from NGOs or other entities. Therefore, understanding the stress level in postdisaster infrastructure is critical for community recovery. This paper presents a new framework to (i) explore and investigate varying functional stress level in infrastructure under various disaster scenarios and (ii) develop strategies for alleviating increased stress levels in order to facilitate the recovery process. The research framework is explained using a hypothetical situation focusing on the operation of power facilities in a postdisaster situation. The proposed unique approach enables the development of sustainable mitigation strategies by relieving the stress level in critical infrastructure while ensuring to meet recovery demands at an acceptable level.

Application of Parameters-Free Adaptive Clonal Selection in Optimization of Construction Site Utilization Planning

Wang, Xi,Deshpande, Abhijeet S.,Dadi, Gabriel B. Korea Institute of Construction Engineering and Ma 2017 Journal of construction engineering and project ma Vol.7 No.2

The Clonal Selection Algorithm (CSA) is an algorithm inspired by the human immune system mechanism. In CSA, several parameters needs to be optimized by large amount of sensitivity analysis for the optimal results. They limit the accuracy of the results due to the uncertainty and subjectivity. Adaptive Clonal Selection (ACS), a modified version of CSA, is developed as an algorithm without controls by pre-defined parameters in terms of selection process and mutation strength. In this paper, we discuss the ACS in detail and present its implementation in construction site utilization planning (CSUP). When applied to a developed model published in research literature, it proves that the ACS are capable of searching the optimal layout of temporary facilities on construction site based on the result of objective function, especially when the parameterization process is considered. Although the ACS still needs some improvements, obtaining a promising result when working on a same case study computed by Genetic Algorithm and Electimze algorithm prove its potential in solving more complex construction optimization problems in the future.

STEADY-STATE TEMPERATURE ANALYSIS TO 2D ELASTICITY AND THERMO-ELASTICITY PROBLEMS FOR INHOMOGENEOUS SOLIDS IN HALF-PLANE

KIRTIWANT P. GHADLE,ABHIJEET B. ADHE 한국산업응용수학회 2020 Journal of the Korean Society for Industrial and A Vol.24 No.1

The concept of temperature distribution in inhomogeneous semi-infinite solids is examined by making use of direct integration method. The analysis is done on the solution of the in-plane steady state heat conduction problem under certain boundary conditions. The method of direct integration has been employed, which is then reduced to Volterra integral equation of second kind, produces the explicit form analytical solution. Using resolvent- kernel algorithm, the governing equation is solved to get present solution. The temperature distribution obtained and calculated numerically and the relation with distribution of heat flux generated by internal heat source is shown graphically.