Segmentation-free approaches of computer vision for automatic calibration of digital and analog instruments

Utilização de Técnicas de Processamento de Imagens e Classificação de Padrões no Reconhecimento de Dígitos em Imagens de Medidores de Consumo de Gás Natural

“…Com respeito ao processamento das imagens de medidores, os trabalhos apresentam o emprego de variadas técnicas, dentre as quais a transformação da imagem em tons de cinza (EDWARD, 2013), segmentação por limiarização (ALEXANDRIA, 2004;ZHAO et al, 2009), morfologia matemática (LEI et al, 2010 e rotulação de componentes conexos (OLIVEIRA et al, 2009). Para o reconhecimento dos dígitos, técnicas como Redes Neurais Artificiais (RNA) VANETTI et al, 2012), classificação baseada na distância mínima (NAVA-ORTIZ et al, 2011), correlação cruzada (BELAN et al, 2013), entre outras, são utilizadas. São tomadas como base diversas características das imagens dos dígitos, tais como histograma de projeções de pixels (CASTELLS-RUFAS; CARRABINA, 2006), tipo de traços retos ou curvos no dígito (SHU et al, 2007), momentos invariantes (BAI et al, 2010), dentre outras.…”

An automatic document processing system for medical data extraction

“…Layout analysis has its roots in image segmentation algorithms, and is a fundamental step towards document understanding, in which the logical relations between document components are fully exploited. Image segmentation [18,19] and text region extraction [20][21][22] are one of the most debated issues in the document images analysis [17] and many problems are currently unresolved. Over the last two decades, several techniques have been proposed, all referable to three classes; bottom-up algorithms, topdown algorithms and hybrid algorithms [23].…”

Automatic Calibration System for Digital-Display Vibrometers Based on Machine Vision

“…Most of the digital-display vibrometers could not be calibrated by the ordinary automatic calibration system directly because of no output or interface except the display on the vibrometers for cost considerations. In the recent years, machine vision technology has widely been applied in automatic systems [8][9][10][11][12][13][14][15][16][17]. A digital camera can be applied to replace human eyes to capture the images of digital or analog displays, and then the captured images are transmitted to a computer, in which the displays are recognized by some image recognition algorithms.…”

“…P.A. Belan and S.A. Araujo et al proposed a segmentation-free algorithm based on template matching to read the digital display [15].…”

“…Besides, recognition of the decimal point has not been considered in many studies [11,12,15]. Furthermore, a large number of digital-display vibrometers to be calibrated should be installed on the vibration table of a vibration exciter since their sensing heads and displays are integrated together into a package, thus the display values may be vibrating during calibrating at a frequency as high as 160Hz, which will result in a blurry image and lower recognition rate because of the limited acquisition speed of the camera.…”