Tess4j maven demo[通俗易懂]

Tess4j maven demo[通俗易懂]tess4j实现文字识别Demo,下面为内容实现源码,内容仅为一个demo,demo下载地址:tess4jDemopublicclassTess4JTest{privatestaticfinalLoggerlogger=LoggerFactory.getLogger(newLoggHelper().toString());staticfinaldo…

大家好,又见面了,我是你们的朋友全栈君。


tess4j 实现文字识别Demo,下面为内容实现源码,内容仅为一个demo,demo下载地址:tess4jDemo

public class Tess4JTest {

    private static final Logger logger = LoggerFactory.getLogger(new LoggHelper().toString());
    static final double MINIMUM_DESKEW_THRESHOLD = 0.05d;
    ITesseract instance;

    private final String datapath = "src/test/resources";
    private final String testResourcesDataPath = "src/test/resources/test-data";
    private final String testResourcesLanguagePath = "src/test/resources/tessdata";

    @BeforeClass
    public static void setUpClass() throws Exception {
    }

    @AfterClass
    public static void tearDownClass() throws Exception {
    }

    @Before
    public void setUp() {
        instance = new Tesseract();
        instance.setDatapath(new File(datapath).getPath());
    }

    @After
    public void tearDown() {
    }

    /**
     * Test of doOCR method, of class Tesseract.
     * 根据图片文件进行识别
     * @throws Exception while processing image.
     */
    @Test
    public void testDoOCR_File() throws Exception {
        logger.info("doOCR on a jpg image");
        File imageFile = new File(this.testResourcesDataPath, "0099.png");
        //set language
        instance.setDatapath(testResourcesLanguagePath);
        instance.setLanguage("chi_sim");
        String result = instance.doOCR(imageFile);
        logger.info(result);
    }

    /**
     * Test of doOCR method, of class Tesseract.
     * 根据图片流进行识别
     * @throws Exception while processing image.
     */
    @Test
    public void testDoOCR_BufferedImage() throws Exception {
        logger.info("doOCR on a buffered image of a PNG");
        File imageFile = new File(this.testResourcesDataPath, "ocr.png");
        BufferedImage bi = ImageIO.read(imageFile);

        //set language
        instance.setDatapath(testResourcesLanguagePath);
        instance.setLanguage("chi_sim");

        String result = instance.doOCR(bi);
        logger.info(result);
    }

    /**
     * Test of getSegmentedRegions method, of class Tesseract.
     * 得到每一个划分区域的具体坐标
     * @throws java.lang.Exception
     */
    @Test
    public void testGetSegmentedRegions() throws Exception {
        logger.info("getSegmentedRegions at given TessPageIteratorLevel");
        File imageFile = new File(testResourcesDataPath, "ocr.png");
        BufferedImage bi = ImageIO.read(imageFile);
        int level = TessPageIteratorLevel.RIL_SYMBOL;
        logger.info("PageIteratorLevel: " + Utils.getConstantName(level, TessPageIteratorLevel.class));
        List<Rectangle> result = instance.getSegmentedRegions(bi, level);
        for (int i = 0; i < result.size(); i++) {
            Rectangle rect = result.get(i);
            logger.info(String.format("Box[%d]: x=%d, y=%d, w=%d, h=%d", i, rect.x, rect.y, rect.width, rect.height));
        }

        assertTrue(result.size() > 0);
    }


    /**
     * Test of doOCR method, of class Tesseract.
     * 根据定义坐标范围进行识别
     * @throws Exception while processing image.
     */
    @Test
    public void testDoOCR_File_Rectangle() throws Exception {
        logger.info("doOCR on a BMP image with bounding rectangle");
        File imageFile = new File(this.testResourcesDataPath, "ocr.png");
        //设置语言库
        instance.setDatapath(testResourcesLanguagePath);
        instance.setLanguage("chi_sim");
        //划定区域
        // x,y是以左上角为原点,width和height是以xy为基础
        Rectangle rect = new Rectangle(84, 21, 15, 13);
        String result = instance.doOCR(imageFile, rect);
        logger.info(result);
    }

    /**
     * Test of createDocuments method, of class Tesseract.
     * 存储结果
     * @throws java.lang.Exception
     */
    @Test
    public void testCreateDocuments() throws Exception {
        logger.info("createDocuments for png");
        File imageFile = new File(this.testResourcesDataPath, "ocr.png");
        String outputbase = "target/test-classes/docrenderer-2";
        List<RenderedFormat> formats = new ArrayList<RenderedFormat>(Arrays.asList(RenderedFormat.HOCR, RenderedFormat.TEXT));

        //设置语言库
        instance.setDatapath(testResourcesLanguagePath);
        instance.setLanguage("chi_sim");

        instance.createDocuments(new String[]{imageFile.getPath()}, new String[]{outputbase}, formats);
    }

    /**
     * Test of getWords method, of class Tesseract.
     * 取词方法
     * @throws java.lang.Exception
     */
    @Test
    public void testGetWords() throws Exception {
        logger.info("getWords");
        File imageFile = new File(this.testResourcesDataPath, "ocr.png");

        //设置语言库
        instance.setDatapath(testResourcesLanguagePath);
        instance.setLanguage("chi_sim");

        //按照每个字取词
        int pageIteratorLevel = TessPageIteratorLevel.RIL_SYMBOL;
        logger.info("PageIteratorLevel: " + Utils.getConstantName(pageIteratorLevel, TessPageIteratorLevel.class));
        BufferedImage bi = ImageIO.read(imageFile);
        List<Word> result = instance.getWords(bi, pageIteratorLevel);

        //print the complete result
        for (Word word : result) {
            logger.info(word.toString());
        }
    }

    /**
     * Test of Invalid memory access.
     * 处理倾斜
     * @throws Exception while processing image.
     */
    @Test
    public void testDoOCR_SkewedImage() throws Exception {
        //设置语言库
        instance.setDatapath(testResourcesLanguagePath);
        instance.setLanguage("chi_sim");

        logger.info("doOCR on a skewed PNG image");
        File imageFile = new File(this.testResourcesDataPath, "ocr_skewed.jpg");
        BufferedImage bi = ImageIO.read(imageFile);
        ImageDeskew id = new ImageDeskew(bi);
        double imageSkewAngle = id.getSkewAngle(); // determine skew angle
        if ((imageSkewAngle > MINIMUM_DESKEW_THRESHOLD || imageSkewAngle < -(MINIMUM_DESKEW_THRESHOLD))) {
            bi = ImageHelper.rotateImage(bi, -imageSkewAngle); // deskew image
        }

        String result = instance.doOCR(bi);
        logger.info(result);
    }

}
版权声明:本文内容由互联网用户自发贡献,该文观点仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 举报,一经查实,本站将立刻删除。

发布者:全栈程序员-用户IM,转载请注明出处:https://javaforall.cn/130445.html原文链接:https://javaforall.cn

【正版授权,激活自己账号】: Jetbrains全家桶Ide使用,1年售后保障,每天仅需1毛

【官方授权 正版激活】: 官方授权 正版激活 支持Jetbrains家族下所有IDE 使用个人JB账号...

(0)


相关推荐

发表回复

您的电子邮箱地址不会被公开。

关注全栈程序员社区公众号