要实现的功能
1.图片识别表格化重建
2.保存识别记录,可以查看自己的记录
3.分析记录并统计总结
4.能够将所有的记录形成一个完整的个人总结性表格
部分代码:
package org.example;//import com.sun.media.sound.InvalidFormatException; import net.sourceforge.tess4j.ITesseract; import net.sourceforge.tess4j.Tesseract; import net.sourceforge.tess4j.TesseractException; import org.apache.poi.openxml4j.exceptions.InvalidFormatException; import org.apache.poi.ss.usermodel.*; import java.io.File; import java.io.FileOutputStream; import java.io.IOException; public class Main { public static void main(String[] args) throws InvalidFormatException, IOException, TesseractException { ITesseract instance = new Tesseract(); instance.setDatapath("src/main/resources/tessdata");
instance.setLanguage("chi_sim"); String result = instance.doOCR(new File("src/main/resources/image.png")); String[] lines = result.split("\r?\n"); Workbook workbook = WorkbookFactory.create(new File("src/main/resources/table.xlsx")); Sheet sheet = workbook.getSheetAt(0); int rowCount = 0; for (String line : lines) { Row row = sheet.createRow(rowCount++); int columnCount = 0; for (String word : line.split("\s+")) { Cell cell = row.createCell(columnCount++); cell.setCellValue(word); } } File file = new File("src/main/resources/table_from_image.xlsx"); workbook.write(new FileOutputStream(file)); workbook.close(); } }
<!DOCTYPE html> <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> <title>菜鸟教程</title> <link rel="stylesheet" href="css/side.css"> </head> <body> <div class="sidenav"> <a href="http://localhost:8080/imageExcel_war_exploded/A1.html">关于我们</a> <a href="http://localhost:8080/imageExcel_war_exploded/A2.html">数据统计</a> <a href="http://localhost:8080/imageExcel_war_exploded/A3.html">我的记录</a> <a href="http://localhost:8080/imageExcel_war_exploded/A4.html">图片转化</a> </div> <div id="tabs-1" style="display: block"> <form action="SubwayLine" > <table style="border-width: 0; width: 100%"> <tr> <table border="1" style="border-left-color: #B0C4DE; border-bottom-color: #B0C4DE; width: 100%;border-top-style: solid; border-top-color: #B0C4DE; border-right-style: solid; border-left-style: solid; height: 250px; border-right-color: #B0C4DE; border-bottom-style: hidden"> <tr align="center"><td align="center" colspan="2">石家庄铁道大学北京地铁线路查询</td></tr> <tr><td style="width: 30%" align="center">线路名称:</td><td style="width: 70%" align="center"> <select name="line" style="height:40px;width:300px;"> <option value="1号线">1号线</option> <option value="2号线">2号线</option> <option value="4号线">4号线</option> </select></td></tr> <tr> <td style="width: 50%" align="center" colspan="2"><input type="submit" style="height:40px;width:300px;" value="查询"/></td> </tr> </table> </tr> </table> </form> </div> <hr /> <div style="text-align: center; width: 100%; font-size: 12px; color: #333;">©版权所有:石家庄铁道大学信息科学与技术学院</div> </body> </html>
标签:String,表格,系统,构建,File,import,new,main,resources From: https://www.cnblogs.com/rsy-bxf150/p/17298997.html