Ocr 异步获取作业结果

{
  "public_id": "c5848676-5a28-48c5-b15e-d66d67b1cbaa",
  "status": "finished",
  "error": null,
  "results": {
    "microsoft": {
      "error": null,
      "id": "d60ba93c-fb51-462a-a814-1bf253bb6800",
      "final_status": "finished",
      "raw_text": "International Journal of Science and Research (IJSR), India Online ISSN: 2319-7064\nAn Introduction to the Process of Optical Character Recognition\nUmal Patel1 1 Department of Computer Engineering L D College Of Engineering, Gujarat Technological University, Gujarat, India\nAbstract: This paper presents an overview of methods and techniques used for feature extraction that helps in efficient classification of the alphabets and numbers of English language. Character recognition has long been a essential area for research since years. Recognition of character is a minor work for humans, but to make a computer program that does character recognition is extremely difficult. Hence to make a machine recognize the characters and efficiently determine a pattern has been the primary concern for researchers now days This paper discusses various offline and online Optical Character Recognition Techniques (OCR).\nKeywords: OCR, online, offline, online, zoning, euler number.\n1. Introduction\nOCR is an approach that provides a full alphanumeric recognition of printed or handwritten characters at electronically by simply scanning them and generating into a form that can be scanned through a scanner and then the recognition engine of the OCR system interpret the images and turn images of handwritten or printed characters into ASCII data (machine-readable characters).Character recognition also popularly referred as optical character recognition (OCR) is a field of research that has immense potential in future where we want to track and locate every piece of information being exchanged. The problem with the hand written text is due to uncertainties such as variation in calligraphy over period of time, similarity in text, variation in styles of writing [3] The character recognition system helps in making the communication between a human and a computer easy.[4] The character recognition is basically classified into two types: offline handwritten text recognition, online handwritten text recognition. Offline means the text written on the plain paper or sheet and then the writing is usually captured optically by a scanner and the completed writing is available as an image. Online means the text written on any digital devices such as tablets using stylus i.e. the two dimensional coordinates of successive points are represented as a function of time and the order of strokes made by the writer are also available.[6]\n2. Applications recognition\nof optical character\nThe area of OCR is becoming an integral part of document scanners, and is used in many applications such as postal processing, script recognition, banking, security (i.e. passport authentication) and language identification, document reading, mail sorting, signature verification, writer identification., license plate recognition system, smart card processing system, automatic data entry, bank cheque /DD processing, money counting machine, postal automation, address and zip code recognition etc many organizations are depending on OCR systems to eliminate the human interactions for better performance and efficiency [2,4,6,7].\n3. Potential problem areas for OCR\n1. The same characters differ in sizes, shapes and styles from person to person and even from time to time with the same person. The source of confusion is the high level of abstraction: there are thousands styles of type in common use plus variations in calligraphy and a character recognition program must recognize most of these.\n2. Like any image, visual characters are subject to spoilage due to noise. Some images containing characters are already blurred or not clear which makes them difficult to process. Noise consists of random changes to a pattern, particularly near the edges. A character with much noise may be interpreted as a completely different character by a computer program.\n3. There are no hard-and-fast rules that define the appearance of a visual character. Hence rules need to be heuristically deduced from the samples.\n4. Phases of OCR\nData Acquisition\nPre processing\nSegmentation\nNormalization\nFeature Extraction\nClassification\nPost Processing\n155\nVolume 2 Issue 5, May 2013 www.ijsr.net\nInternational Journal of Science and Research (IJSR), India Online ISSN: 2319-7064\n1. Data Acquisition\nMost Important initial phase in OCR is to gather the image from either device sensor like PDA or tablets in case on online recognition or getting the images containing characters directly for offline recognition.\nIn Image acquisition, the recognition system acquires a scanned image as an input image. The image should have a specific format such as JPEG, BMP etc. This image is acquired through a scanner, digital camera or any other suita