Based on a previous work on handwritten Japanese kanji character recognition, a postprocessing system for handwritten Japanese address recognition is proposed. Basically, the recognition system is composed of CombNET-II, a general-purpose large-scale character recognizer and MMVA, a modified majority voting system. Beginning with a set of character candidates, produced by a character recognizer for each character that composes the input word and a lexicon, an interpretation to the input word is generated. MMVA is used in the postprocessing stage to select the interpretation that accumulates the highest score. In the case of more than one possible interpretation, the Conflict Analyzing System calls the character recognizer again to generate scores for each character that composes each interpretation to determine the final output word. The proposed word recognition system was tested with 2 sets of handwritten Japanese city names, and recognition rates higher than 99% were achieved, demonstrating the effectiveness of the method.

We present a novel adaptive method to improve the binarization quality of degraded word color images. The objective of this work is to solve a nonlinear problem concerning the binarization quality, that is, to achieve edge enhancement and noise reduction in images. The digitized data used in this work were extracted automatically from real world photos. The motion of objects with reference to static camera and bad environmental conditions provoked serious quality problems on those images. Conventional methods, such as the nonlinear adaptive filter method proposed by Mo, or Otsu's method cannot produce satisfactory binarization results for those types of degraded images. Among other problems, we note mainly that contrast (between shapes and backgrounds) varies greatly within every degraded image due to non-uniform illumination. The proposed method is based on the automatic extraction of background information, such as luminance distribution to adaptively control the intensity levels, that is, without the need for any manual fine-tuning of parameters. Consequently, the new method can avoid noise or inappropriate shapes in the output binary images. Otsu's method is also applied to automatic threshold selection for classifying the pixels into background and shape pixels. To demonstrate the efficiency and the feasibility of the new adaptive method, we present results obtained by the binarization system. The results were satisfactory as we expected, and we have concluded that they can be used successfully as data in further processing such as segmentation or extraction of characters. Furthermore, the method helps to increase the eventual efficiency of a recognition system for poor-quality word images, such as number plate photos with non-uniform illumination and low contrast.

Basic block vectorization consists in realizing instruction-level parallelism inside basic blocks in order to generate SIMD instructions and thus speedup data processing. It is however problematic, because the vectorized program may actually be slower than the original one. Therefore, it would be useful to predict beforehand whether or not vectorization will actually produce any speedup. This paper proposes to do so by expressing vectorization profitability as a classification problem, and by predicting it using a machine learning technique called support vector machine (SVM). It considers three compilers (icc, gcc and llvm), and a benchmark suite made of 151 loops, unrolled with factors ranging from 1 to 20. The paper further proposes a technique that combines the results of two SVMs to reach 99% of accuracy for all three compilers. Moreover, by correctly predicting unprofitable vectorizations, the technique presented in this paper provides speedups of up to 2.16 times, 2.47 times and 3.83 times for icc, gcc and LLVM, respectively (9%, 18% and 56% on average). It also lowers to less than 1% the probability of the compiler generating a slower program with vectorization turned on (from more than 25% for the compilers alone).

Modern optimizing compilers tend to be conservative and often fail to vectorize programs that would have benefited from it. In this paper, we propose a way to predict the relevant command-line options of the compiler so that it chooses the most profitable vectorization strategy. Machine learning has proven to be a relevant approach for this matter: fed with features that describe the software to the compiler, a machine learning device is trained to predict an appropriate optimization strategy. The related work relies on the control and data flow graphs as software features. In this article, we consider tensor contraction programs, useful in various scientific simulations, especially chemistry. Depending on how they access the memory, different tensor contraction kernels may yield very different performance figures. However, they exhibit identical control and data flow graphs, making them completely out of reach of the related work. In this paper, we propose an original set of software features that capture the important properties of the tensor contraction kernels. Considering the Intel Merom processor architecture with the Intel Compiler, we model the problem as a classification problem and we solve it using a support vector machine. Our technique predicts the best suited vectorization options of the compiler with a cross-validation accuracy of 93.4%, leading to up to a 3-times speedup compared to the default behavior of the Intel Compiler. This article ends with an original qualitative discussion on the performance of software metrics by means of visualization. All our measurements are made available for the sake of reproducibility.