177 Chapters
Medium 9781601322548

Improved Shadow Removal for Unstructured Road Detection

Hamid R. Arabnia; Leonidas Deligiannidis; Joan Lu; Fernando G. Tinetti; Jane You; George Jandieri; Gerald Schaefer; Ashu M. G. Solo; and Vladimir Volkov (Editors) Mercury Learning and Information PDF

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'13 |

413

Improved Shadow Removal for Unstructured Road

Detection

Ngouh Njikam Ahmed Salim, Xu Cheng, Degui Xiao

College of Information Science and Engineering, Hunan University, Changsha, P.R.China

Abstract - One of the greatest challenges for vision-based road detection is the presence of shadows and other vehicles.

It’s particularly challenging to detect unstructured road when it has both shadowed and non shadowed area since the presence of shadows can cause hindrance and shape distortion of objects which may result in false detection of road. Shadows can also cause a significant problem in road detection since shadow boundaries may be incorrectly recognized or simply hinder the road detection process leading to a higher false rate detection. To tackle those issues, this paper introduces an effective road recognition system using an image processing method to eliminate or reduce considerably the presence of strong shadows for unstructured road detection. Our method’s main novelties are the use of a simple and effective shadow detection and removal algorithm using bilateral filter combined with a model-based classifier.

See All Chapters
Medium 9781601322548

Automatic Navigation through a Single 2D Image using Vanishing Point

Hamid R. Arabnia; Leonidas Deligiannidis; Joan Lu; Fernando G. Tinetti; Jane You; George Jandieri; Gerald Schaefer; Ashu M. G. Solo; and Vladimir Volkov (Editors) Mercury Learning and Information PDF

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'13 |

193

Automatic Navigation through a Single 2D Image using

Vanishing Point

Geetha Kiran A1, Murali S2

1

2

Computer Science and Engineering, Malnad College of Engineering, Hassan, Karnataka, India

Computer Science and Engineering, Maharaja Institute of Technology, Mysore, Karnataka, India

Abstract -

Image based navigation paradigms have recently emerged as an interesting alternative to conventional methods. This paper focuses on the problem of automatic navigation through Road scenes that mainly consist of single vanishing point. The algorithm infers frontier information directly from the image to navigate through Road images. The major cue to terminate the navigation is the vanishing point. The proposed algorithm has 3 major steps: First, the preprocessing techniques are applied to the given image to find the vanishing point.

Second, compute the distance from the ground truth position to the vanishing point which is used as the termination point for navigation. Finally, create the navigation by cropping the image. Our approach is fully automatic, since it needs no human intervention. The approach finds applications, mainly in assisting autonomous cars, virtual walk through ancient time images and in forensics. Qualitative and quantitative experiments on nearly 150 Real-road images in different scenarios show that the proposed algorithm is more efficient and accurate.

See All Chapters
Medium 9781601322548

Vision-Based Localization and Text Chunking of Nutrition Fact Tables on Android Smartphones

Hamid R. Arabnia; Leonidas Deligiannidis; Joan Lu; Fernando G. Tinetti; Jane You; George Jandieri; Gerald Schaefer; Ashu M. G. Solo; and Vladimir Volkov (Editors) Mercury Learning and Information PDF

314

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'13 |

Vision-Based Localization and Text Chunking of Nutrition Fact

Tables on Android Smartphones

Vladimir Kulyukin1, Aliasgar Kutiyanawala1, Tanwir Zaman1, and Stephen Clyde2

1

Department of Computer Science, Utah State University, Logan, UT, USA

2

MDSC Corporation, Salt Lake City, UT, USA

Abstract—Proactive nutrition management is considered by many nutritionists and dieticians as a key factor in reducing and controlling cancer, diabetes, and other illnesses related to or caused by mismanaged diets. As more and more individuals manage their daily activities with smartphones, smartphones have the potential to become proactive diet management tools.

While there are many vision-based mobile applications to process barcodes, there is a relative dearth of vision-based applications for extracting other useful nutrition information items from product packages, e.g., nutrition facts, caloric contens, and ingredients. In this paper, we present a visionbased algorithm to localize aligned nutrition fact tables

See All Chapters
Medium 9781601322548

Automated coronary artery segmentation and calcified/non-calcified plaque measurement

Hamid R. Arabnia; Leonidas Deligiannidis; Joan Lu; Fernando G. Tinetti; Jane You; George Jandieri; Gerald Schaefer; Ashu M. G. Solo; and Vladimir Volkov (Editors) Mercury Learning and Information PDF

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'13 |

819

Automated coronary artery segmentation and calcified/non-calcified plaque measurement

Pei-Kai Hung1, Chun-You Liu1, Chia-Yun Hsu1, Chao-Yu Huang1, Wen-Jeng Lee2, Tzung-Dau Wang3 and Chung-Ming Chen1,*

1

Institute of biomedical engineering, National Taiwan university, Taipei, Taiwan

2

Department of Medical Imaging, National Taiwan university hospital, Taipei, Taiwan

3

Department of Internal Medicine, National Taiwan university hospital, Taipei, Taiwan

Abstract - Construction of reasonable coronary artery trees and quantitative analysis on vulnerable plaque are essential in the diagnosis of coronary artery disease. An automated algorithm is proposed for both coronary artery tree reconstruction and plaque detection in this study. Discrete wavelet transform (DWT) is introduced to prevent leakage from region growing and enhance the discrimination between coronary artery tree and surrounding tissues. Automated quantitative analysis of both calcified and non-calcified plaques is achieved. To derive an accurate volume estimate of a calcified plaque, the calcified plaque is identified from the coronary artery tree reconstructed from the CT image with contrast agent and its volume is derived from the CT image without contrast agent. The proposed method has been tested on eight sets of MSCT scan images with reasonable results.

See All Chapters
Medium 9781601322548

Iris texture feature extraction with orthogonal polynomials

Hamid R. Arabnia; Leonidas Deligiannidis; Joan Lu; Fernando G. Tinetti; Jane You; George Jandieri; Gerald Schaefer; Ashu M. G. Solo; and Vladimir Volkov (Editors) Mercury Learning and Information PDF

Int'l Conf. IP, Comp. Vision, and Pattern Recognition | IPCV'13 |

159

Iris texture feature extraction with orthogonal polynomials

R. Krishnamoorthy 1, G. Annapoorani 1 and Anil K. Kaushik2

1. Image Research and Information Science Laboratory, Department of Computer Science and Engineering,

Bharathidasan Institute of Technology, Anna University, Tiruchirappalli – 620 024, India.

2. Department of Electronics and Information Technology, Ministry of Communication and Information Technology,

New Delhi, India.

Abstract- In this paper, a feature extraction technique with orthogonal polynomials based computational model to accurately extract local texture in iris images is presented. Initially, the normalized input iris image is subjected with the orthogonal polynomials model and the model coefficients are obtained. The model coefficients are subjected to statistical hypothesis testing with Hartley’s test so as to extract the signal components due to texture in the iris images and simultaneously separating out the noise components. These model coefficients due to the orthogonal polynomials model, are utilized to represent the iris texture patterns along with their zonal positions, as the locations of the micro texture present in the image analysis is considered to be significant. The texture primitives thus extracted are represented with a decimal number and used for feature extraction.

See All Chapters

See All Chapters