java 图片识别 tess4j_JAVA使用Tess4J进行ocr识别

Tess4J是对Tesseract OCR API.的Java JNA 封装。使java能够通过调用Tess4J的API来使用Tesseract OCR。支持的格式：TIFF,JPEG,GIF,PNG,BMP,JPEG,and PDF

Tesseract 的github地址：https://github.com/tesseract-ocr/tesseract

Tess4J的github地址：https://github.com/nguyenq/tess4j

Tess4J API 提供的功能：

1、直接识别支持的文件

2、识别图片流

3、识别图片的某块区域

4、将识别结果保存为 TEXT/ HOCR/ PDF/ UNLV/ BOX

5、通过设置取词的等级，提取识别出来的文字

6、获得每一个识别区域的具体坐标范围

7、调整倾斜的图片

8、裁剪图片

9、调整图片分辨率

10、从粘贴板获得图像

11、克隆一个图像(目的：创建一份一模一样的图片，与原图在操作修改上，不相 互影响)

12、图片转换为二进制、黑白图像、灰度图像

13、反转图片颜色

demo.java:

/**

* 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, “ocr.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 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 formats = new ArrayList(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 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);

}