DIBCO 2009 is the first International Document Image Binarization Contest organized in the context of ICDAR 2009 conference. The general objective of the contest is to identify current advances in document image binarization using established evaluation performance measures. This paper describes the contest details including the evaluation measures used as well as the performance of the 43 submitted methods along with a short description of each method.

H-DIBCO 2010 is the International Document Image Binarization Contest which is dedicated to handwritten document images organized in conjunction with ICFHR 2010 conference. The general objective of the contest is to identify current advances in handwritten document image binarization using meaningful evaluation performance measures. This paper reports on the contest details including the evaluation measures used as well as the performance of the 17 submitted methods along with a short description of each method.

Autonomous vehicles integrate complex software stacks for realizing the necessary iterative perception, planning, and action operations. One of the foundational layers of such stacks is the perception one which is comprised of localization, detection, and recognition algorithms for understanding the location and the driving environment around the vehicle. More precisely, localization aims to identify the location of the vehicle on a global coordinate system and is considered one of the most critical parts in the stack since its accuracy and robustness affects the subsequent algorithms of the perception layer and also the following planning and action layers. Due to the rapid and significant interest in self-driving cars, several localization techniques have been proposed with different directions and approaches. Algorithms using prior maps are currently considered the most accurate ones and found almost in all current self-driving car prototypes. Thus, in this paper, we categorize, discuss and analyze the state-of-the-art map-based localization techniques in an attempt to examine their potentials and limitations. We first present techniques and approaches that aim to match prior maps with on-board observations from different sensor modalities. We then review methods that handle the localization problem as a probabilistic one and finally, we also go through the emerging domain of deep-learning localization algorithms and examine their potential in self-driving cars. For all three categories, we provide comparison tables and necessary insights for the optimal localization system design based on different requirements, specifications, and sensor configurations.

Deep convolutional neural networks (CNNs) are investigated in the context of computer-aided diagnosis (CADx) of breast cancer. State-of-the-art CNNs are trained and evaluated on two mammographic datasets, consisting of ROIs depicting benign or malignant mass lesions. The performance evaluation of each examined network is addressed in two training scenarios: the first involves initializing the network with pre-trained weights, while for the second the networks are initialized in a random fashion. Extensive experimental results show the superior performance achieved in the case of fine-tuning a pretrained network compared to training from scratch.

Document image binarization is of great importance in the document image analysis and recognition pipeline since it affects further stages of the recognition process. The evaluation of a binarization method aids in studying its algorithmic behavior, as well as verifying its effectiveness, by providing qualitative and quantitative indication of its performance. This paper addresses a pixel-based binarization evaluation methodology for historical handwritten/machine-printed document images. In the proposed evaluation scheme, the recall and precision evaluation measures are properly modified using a weighting scheme that diminishes any potential evaluation bias. Additional performance metrics of the proposed evaluation scheme consist of the percentage rates of broken and missed text, false alarms, background noise, character enlargement, and merging. Several experiments conducted in comparison with other pixel-based evaluation measures demonstrate the validity of the proposed evaluation scheme.