Review of automatic text summarization techniques & methods

Tooth segmentation acts as a crucial and fundamental role in dentistry for doctors to make diagnosis and treatment plans. In this paper, we propose a Two-Stage Attention Segmentation Network (TSASNet) on dental panoramic X-ray images to address the issues suffered in the tooth boundary and tooth root segmentation task which are caused by the low contrast and uneven intensity distribution. We firstly adopt an attention model which is embedded with global and local attention modules to roughly localize the tooth region in the first stage. Without any interactive operator, the attention model so constructed can automatically aggregate pixel-wise contextual information and identify coarse tooth boundaries. To better obtain final boundary information, we use a fully convolutional network as the second stage to further segment the real tooth area from the attention maps obtained from the first stage. The effectiveness of TSASNet is substantiated on the benchmark dataset containing 1,500 dental panoramic X-ray images, our proposed method achieves 96.94% of accuracy, 92.72% of dice and 93.77% of recall, significantly superior to the current state-of-the-art methods.

TSASNet: Tooth segmentation on dental panoramic X-ray images by Two-Stage Attention Segmentation Network

In the practical reality of face recognition applications, the human face can have only a limited number of training images. However, it is known that, in general, increasing the number of training images also increases the performance of face recognition systems. In this case, a new set of training samples can be generated from the original samples, using the symmetry property of the face. Although many face recognition methods have been proposed in the literature, a robust face recognition system is still a challenging task. In this paper, recognition performance was improved by using the property of face symmetry. Moreover, the effects of illumination and pose variations were reduced. A Two-Dimensional Discrete Wavelet Transform, based on the Local Binary Pattern, which is a new approach for face recognition using symmetry, has been presented. The method has three main stages, preprocessing, feature extraction, and classification. A Two-Dimensional Discrete Wavelet Transform with Single-Level and Gaussian Low-Pass Filter were used, separately, for preprocessing. The Local Binary Pattern, Gray Level Co-Occurrence Matrix, and the Gabor filter were used for feature extraction, and the Euclidean Distance was used for classification. The proposed method was implemented and evaluated using the Olivetti Research Laboratory (ORL) and Yale datasets. This study also examined the importance of the preprocessing stage in a face recognition system. The experimental results showed that the proposed method had a recognition accuracy of 100%, for both the ORL and Yale datasets, and these recognition rates were higher than the methods in the literature.

Face Recognition with Symmetrical Face Training Samples Based on Local Binary Patterns and the Gabor Filter

Panoramic X-ray images are the major source used in field of dental image segmentation. However, such images suffers from the disturbances like low contrast, presence of jaw bones, nose bones, spinal bone, and artifacts. Thus, to observe these images manually is a tedious task, requires expertise of dentist and is time consuming. Hence, there is need to develop an automated tool for teeth segmentation. Recently, few deep models have been developed for dental image segmentation. But, such models possess large number of training parameters, thus making the segmentation a very complex task. Also, these models are based only on conventional CNN and lacks in exploiting multimodal CNN features for dental image segmentation. Thus, to address these issues, a novel encoder-decoder model based on multimodal-feature extraction for automatic segmentation of teeth area is proposed. The encoder has three different CNN based architectures: conventional CNN, atrous-CNN, and separable CNN to encode rich contextual information. Whereas decoder contains a single stream of deconvolutional layers for segmentation. The proposed model is tested on 1500 panoramic X-ray images and uses very less parameters when compared to state-of-the-art methods. Besides this, the precision and recall are 95.01% and 94.06%, which out performs the state-of-the art methods.

Exploiting multimodal CNN architecture for automated teeth segmentation on dental panoramic X-ray images

espanolLa generacion automatica de resumenes consiste en sintetizar en un texto corto la informacion mas relevante contenida en documentos, y permite reducir los problemas generados por la sobrecarga de informacion. En este trabajo se presenta un metodo no supervisado de generacion de resumenes extractivos a partir de multiples documentos. En esta propuesta, la conceptualizacion y estructura semantica subyacente del contenido textual se representa en un grafo semantico usando WordNet y se aplica un algoritmo de agrupamiento de conceptos para identificar los topicos tratados en los documentos, con los cuales se evalua la relevancia de las oraciones para construir el resumen. El metodo fue evaluado con corpus de textos de MultiLing 2015, y se usaron metricas de ROUGE para medir la calidad de los resumenes generados. Los resultados obtenidos se compararon con los de otros sistemas participantes en MultiLing 2015, evidenciandose mejoras en la mayoria de los casos. | EnglishThe automatic texts summarization consists in synthesizing in a short text the most relevant information contained in text documents, and allows to reduce the generated problems by the information overload. In this paper, an unsupervised method for extractive multi-document summarization is presented. In this proposal, the conceptualization and underlying semantics structure of the textual content is represented in a semantic graph using WordNet, and a concept clustering algorithm is applied to identifying the topics of the documents set, with which the relevance of the sentences is evaluated to build the summary. The method was evaluated with texts corpus from MultiLing 2015, and ROUGE metrics were used to measure the quality of the generated summaries. The obtained results were compared with those other participant systems in MultiLing 2015, evidencing improves in most of the cases.

/pdf/generacion-de-resumenes-extractivos-de-multiples-documentos-b0lw8rw98a.pdf

Generación de resúmenes extractivos de múltiples documentos usando grafos semánticos

Dental Panoramic Radiograph is often used for age identification and forensic examination in medical evaluations Like most medical images, it has low contrast and high noise Hence for facilitating medical workers in analyze the image, it requires segmentation process to separate foreground and background areas Conventional image segmentation technique used markers to determine the object areas manually Several researches that develop automatic marker for image segmentation based on spatial domain have been conducted However, they are unable to provide satisfactory segmentation result, because it relies on pixel processing and not effective in images with high spatial size Therefore, new automatic marker determination method is needed to overcome this problem This paper proposed a new method for generating automatic marker based on combined directional images from frequency domain for Dental Panoramic Radiograph segmentation This method creates directional images that separate the dental image into vertical and horizontal direction Directional images are combined and used as inputs in automatic marker generation Then the automatic marker can be applied on image segmentation technique, such as Region Growing algorithm Experimental results on 40 dental images showed that the use of proposed automatic marker yields better results than the marker using vertical or horizontal directional image separately With the best value of Misclassification Error (ME), Relative foreground Area Error (RAE) and Accuracy are 78%, 02% and 922% respectively Automatic marker using combined directional images has stability for handling the segmentation of dental images that tend to have vertical and horizontal direction

Generating automatic marker based on combined directional images from frequency domain for Dental Panoramic Radiograph Segmentation

Multi – document as one of summarization type has become more challenging issue than single-document because its larger space and its different content of each document. Hence, some of optimization algorithms consider some criteria in producing the best summary, such as relevancy, content coverage, and diversity. Those weighted criteria based on the assumption that the multi-documents are already located in the same cluster. However, in a certain condition, multi-documents consist of many categories and need to be considered too. In this paper, we propose an inter and intra cluster which consist of four weighted criteria functions (coherence, coverage, diversity, and inter-cluster analysis) to be optimized by using SaDE (Self Adaptive Differential Evolution) to get the best summary result. Therefore, the proposed method will deal not only with the value of compactness quality of the cluster within but also the separation of each cluster. Experimental results on Text Analysis Conference (TAC) 2008 datasets yields better summaries results with average ROUGE-1 on precision, recall, and f - measure 0.77, 0.07, and 0.12 compared to another method that only consider the analysis of intra-cluster.

http://jiki.cs.ui.ac.id/index.php/jiki/article/download/547/397

Eva Firdayanti Bisono

Papers

Generating automatic marker based on combined directional images from frequency domain for Dental Panoramic Radiograph Segmentation

Inter and Intra Cluster on Self-adaptive Differential Evolution for Multi-document Summarization