no message

Plan/pytesseractJsOCR.py

@@ -0,0 +1,18 @@
+import subprocess
+
+from IdentifyModel.cardModel import parse_id_card
+from Plan.AiLLM import extract_entities
+
+
+def pytesseractJs_recognition(validation_type, image, temp_path, file_name, language):
+    try:
+        # 使用 subprocess 執行 JavaScript 代碼，傳遞語言參數
+        subprocess.run(['node', 'pytesseractJsOCR.js', image, language, temp_path + file_name],
+                       capture_output=True,
+                       text=True)
+        with open(temp_path + file_name, 'r') as file:
+            out_ocr_text = file.read()
+            entities = extract_entities(out_ocr_text)
+        return parse_id_card(out_ocr_text, validation_type, entities)
+    except Exception as e:
+        return str(e)

Preprocess/preprocessImg.py

@@ -36,6 +36,7 @@ def preprocess_image001(image):
     denoised = cv2.fastNlMeansDenoising(binary, None, 30, 7, 21)
     return Image.fromarray(denoised)
 
+
 # 方案二
 def preprocess_image002(image):
     # 將 PIL Image 轉換為 numpy array

app.py

@@ -1,6 +1,11 @@
 import os
+import subprocess
+from datetime import datetime
+
 import gradio as gr
+
 from Plan.AiLLM import llm_recognition
+from Plan.pytesseractJsOCR import pytesseractJs_recognition
 from Plan.pytesseractOCR import ocr_recognition
 from Preprocess.preprocessImg import PreprocessImg
 
@@ -28,8 +33,8 @@ def preprocess_image(image):
 # pytesseract OCR
 def Basic_ocr(valid_type, language, preprocessed_images, finish_pre_img):
     if not finish_pre_img:
-        gr.Warning("請先完成圖像預處理！")
-        raise ValueError("請先完成圖像預處理！")
+        gr.Warning("請先執行圖像預處理，再進行分析！")
+        raise ValueError("請先執行圖像預處理，再進行分析！")
 
     # 方案一
     ocr_result_001 = ocr_recognition(preprocessed_images[0], valid_type, language)
@@ -48,8 +53,8 @@ def Basic_ocr(valid_type, language, preprocessed_images, finish_pre_img):
 # AI LLM OCR
 def AiLLM_ocr(valid_type, language, preprocessed_images, finish_pre_img):
     if not finish_pre_img:
-        gr.Warning("請先完成圖像預處理！")
-        raise ValueError("請先完成圖像預處理！")
+        gr.Warning("請先執行圖像預處理，再進行分析！")
+        raise ValueError("請先執行圖像預處理，再進行分析！")
 
     # 方案一
     llm_result_001 = llm_recognition(preprocessed_images[0], valid_type, language)
@@ -65,17 +70,65 @@ def AiLLM_ocr(valid_type, language, preprocessed_images, finish_pre_img):
     return llm_result_001, llm_result_002, llm_result_003, llm_result_004, llm_result_005
 
 
+def pytesseractJs_ocr(valid_type, language, preprocessed_images, finish_pre_img):
+    if not finish_pre_img:
+        gr.Warning("請先執行圖像預處理，再進行分析！")
+        raise ValueError("請先執行圖像預處理，再進行分析！")
+
+    temp_path = 'TempFile/' + datetime.now().strftime('%Y%m%d_%H%M%S') + '/'
+    # 檢查目錄是否存在，如果不存在則建立
+    if not os.path.exists(temp_path):
+        os.makedirs(temp_path)
+
+    image_files = []
+    for i, image in enumerate(preprocessed_images):
+        filename = temp_path + f'preprocessed_image_{i}.png'
+        image.save(filename)
+        image_files.append(filename)
+
+    # 方案一
+    file_name = 'out_pytesseractJs_result_1.txt'
+    out_ocr_text_001 = pytesseractJs_recognition(valid_type, image_files[0], temp_path, file_name, language)
+
+    # 方案二
+    file_name = 'out_pytesseractJs_result_2.txt'
+    out_ocr_text_002 = pytesseractJs_recognition(valid_type, image_files[1], temp_path, file_name, language)
+
+    # file_name = 'out_pytesseractJs_result_2.txt'
+    # 使用 subprocess 執行 JavaScript 代碼，傳遞語言參數
+    # subprocess.run(['node', 'pytesseractJsOCR.js', image_files[1], language, temp_path + file_name], capture_output=True,
+    #                text=True)
+    # with open(temp_path + file_name, 'r') as file:
+    #     out_ocr_text_002 = file.read()
+
+    # 方案三
+    file_name = 'out_pytesseractJs_result_3.txt'
+    out_ocr_text_003 = pytesseractJs_recognition(valid_type, image_files[2], temp_path, file_name, language)
+
+    # 方案四
+    file_name = 'out_pytesseractJs_result_4.txt'
+    out_ocr_text_004 = pytesseractJs_recognition(valid_type, image_files[3], temp_path, file_name, language)
+
+    # 方案五
+    file_name = 'out_pytesseractJs_result_5.txt'
+    out_ocr_text_005 = pytesseractJs_recognition(valid_type, image_files[4], temp_path, file_name, language)
+
+    return out_ocr_text_001, out_ocr_text_002, out_ocr_text_003, out_ocr_text_004, out_ocr_text_005
+
+
 # VIEW
 with gr.Blocks() as demo:
     with gr.Row():
         image_input = gr.Image(type="pil", label="上傳圖片")
-        validation_type = gr.Dropdown(choices=["純文字", "身分證正面", "身分證反面"], label="驗證類別")
-        language_dropdown = gr.Dropdown(choices=languages, value="chi_tra", label="語言")
-
-    with gr.Row():
-        preImg_button = gr.Button("圖片預先處理")
-
+        with gr.Column():
+            validation_type = gr.Dropdown(choices=["全文分析", "身分證正面", "身分證反面"], value='全文分析',
+                                          label="驗證類別")
+            language_dropdown = gr.Dropdown(choices=languages, value="chi_tra", label="語言")
     with gr.Row():
+        with gr.Column():
+            preImg_button = gr.Button("圖片預先處理")
+            gr.Markdown(
+                "<div style='display: flex;justify-content: center;align-items: center;background-color: red;font-weight: bold;text-decoration: underline;font-size: 20px;'>多模態預處理圖像</div>")
         with gr.Column():
             ocr_button = gr.Button("使用 Pytesseract OCR 辨識")
             gr.Markdown(
@@ -84,28 +137,40 @@ with gr.Blocks() as demo:
             llm_button = gr.Button("使用 AI LLM 模型辨識")
             gr.Markdown(
                 "<div style='display: flex;justify-content: center;align-items: center;background-color: red;font-weight: bold;text-decoration: underline;font-size: 20px;'>Package：Bert-base-chinese</div>")
+        with gr.Column():
+            pytesseractJS_button = gr.Button("使用 PytesseractJS 模型辨識")
+            gr.Markdown(
+                "<div style='display: flex;justify-content: center;align-items: center;background-color: red;font-weight: bold;text-decoration: underline;font-size: 20px;'>Package：PytesseractJS</div>")
 
     with gr.Row():
         preprocess_output_001 = gr.Image(type="pil", label="預處理後的圖片-方案一")
         ocr_output_001 = gr.JSON(label="OCR-001-解析結果")
         llm_output_001 = gr.JSON(label="AiLLM-001-解析結果")
+        pytesseractJS_output_001 = gr.JSON(label="PytesseractJS-001-解析結果")
+
     with gr.Row():
         preprocess_output_002 = gr.Image(type="pil", label="預處理後的圖片-方案二")
         ocr_output_002 = gr.JSON(label="OCR-002-解析結果")
         llm_output_002 = gr.JSON(label="AiLLM-002-解析結果")
+        pytesseractJS_output_002 = gr.JSON(label="PytesseractJS-002-解析結果")
 
     with gr.Row():
         preprocess_output_003 = gr.Image(type="pil", label="預處理後的圖片-方案三")
         ocr_output_003 = gr.JSON(label="OCR-003-解析結果")
         llm_output_003 = gr.JSON(label="AiLLM-003-解析結果")
+        pytesseractJS_output_003 = gr.JSON(label="PytesseractJS-003-解析結果")
+
     with gr.Row():
         preprocess_output_004 = gr.Image(type="pil", label="預處理後的圖片-方案四")
         ocr_output_004 = gr.JSON(label="OCR-004-解析結果")
         llm_output_004 = gr.JSON(label="AiLLM-004-解析結果")
+        pytesseractJS_output_004 = gr.JSON(label="PytesseractJS-004-解析結果")
+
     with gr.Row():
         preprocess_output_005 = gr.Image(type="pil", label="預處理後的圖片-方案五")
         ocr_output_005 = gr.JSON(label="OCR-005-解析結果")
         llm_output_005 = gr.JSON(label="AiLLM-005-解析結果")
+        pytesseractJS_output_005 = gr.JSON(label="PytesseractJS-005-解析結果")
 
     # 定義狀態
     finish_pre_img_state = gr.State(False)
@@ -126,4 +191,10 @@ with gr.Blocks() as demo:
                                         preprocessed_images_state, finish_pre_img_state],
                      outputs=[llm_output_001, llm_output_002, llm_output_003, llm_output_004, llm_output_005])
 
+    # pytesseract 按鈕
+    pytesseractJS_button.click(pytesseractJs_ocr, inputs=[validation_type, language_dropdown,
+                                                          preprocessed_images_state, finish_pre_img_state],
+                               outputs=[pytesseractJS_output_001, pytesseractJS_output_002, pytesseractJS_output_003,
+                                        pytesseractJS_output_004, pytesseractJS_output_005])
+
 demo.launch(share=False)

package-lock.json

@@ -0,0 +1,119 @@
+{
+  "name": "OCR-2",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "dependencies": {
+        "tesseract.js": "^5.1.0"
+      }
+    },
+    "node_modules/bmp-js": {
+      "version": "0.1.0",
+      "resolved": "https://registry.npmjs.org/bmp-js/-/bmp-js-0.1.0.tgz",
+      "integrity": "sha512-vHdS19CnY3hwiNdkaqk93DvjVLfbEcI8mys4UjuWrlX1haDmroo8o4xCzh4wD6DGV6HxRCyauwhHRqMTfERtjw=="
+    },
+    "node_modules/idb-keyval": {
+      "version": "6.2.1",
+      "resolved": "https://registry.npmjs.org/idb-keyval/-/idb-keyval-6.2.1.tgz",
+      "integrity": "sha512-8Sb3veuYCyrZL+VBt9LJfZjLUPWVvqn8tG28VqYNFCo43KHcKuq+b4EiXGeuaLAQWL2YmyDgMp2aSpH9JHsEQg=="
+    },
+    "node_modules/is-electron": {
+      "version": "2.2.2",
+      "resolved": "https://registry.npmjs.org/is-electron/-/is-electron-2.2.2.tgz",
+      "integrity": "sha512-FO/Rhvz5tuw4MCWkpMzHFKWD2LsfHzIb7i6MdPYZ/KW7AlxawyLkqdy+jPZP1WubqEADE3O4FUENlJHDfQASRg=="
+    },
+    "node_modules/is-url": {
+      "version": "1.2.4",
+      "resolved": "https://registry.npmjs.org/is-url/-/is-url-1.2.4.tgz",
+      "integrity": "sha512-ITvGim8FhRiYe4IQ5uHSkj7pVaPDrCTkNd3yq3cV7iZAcJdHTUMPMEHcqSOy9xZ9qFenQCvi+2wjH9a1nXqHww=="
+    },
+    "node_modules/node-fetch": {
+      "version": "2.7.0",
+      "resolved": "https://registry.npmjs.org/node-fetch/-/node-fetch-2.7.0.tgz",
+      "integrity": "sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==",
+      "dependencies": {
+        "whatwg-url": "^5.0.0"
+      },
+      "engines": {
+        "node": "4.x || >=6.0.0"
+      },
+      "peerDependencies": {
+        "encoding": "^0.1.0"
+      },
+      "peerDependenciesMeta": {
+        "encoding": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/opencollective-postinstall": {
+      "version": "2.0.3",
+      "resolved": "https://registry.npmjs.org/opencollective-postinstall/-/opencollective-postinstall-2.0.3.tgz",
+      "integrity": "sha512-8AV/sCtuzUeTo8gQK5qDZzARrulB3egtLzFgteqB2tcT4Mw7B8Kt7JcDHmltjz6FOAHsvTevk70gZEbhM4ZS9Q==",
+      "bin": {
+        "opencollective-postinstall": "index.js"
+      }
+    },
+    "node_modules/regenerator-runtime": {
+      "version": "0.13.11",
+      "resolved": "https://registry.npmjs.org/regenerator-runtime/-/regenerator-runtime-0.13.11.tgz",
+      "integrity": "sha512-kY1AZVr2Ra+t+piVaJ4gxaFaReZVH40AKNo7UCX6W+dEwBo/2oZJzqfuN1qLq1oL45o56cPaTXELwrTh8Fpggg=="
+    },
+    "node_modules/tesseract.js": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/tesseract.js/-/tesseract.js-5.1.0.tgz",
+      "integrity": "sha512-2fH9pqWdS2C6ue/3OoGg91Wtv7Rt/1atYu/g0Q1SGFrowEW/kIBkG361hLienHsWe4KWEjxOJBrCQYpIBWG6WA==",
+      "hasInstallScript": true,
+      "dependencies": {
+        "bmp-js": "^0.1.0",
+        "idb-keyval": "^6.2.0",
+        "is-electron": "^2.2.2",
+        "is-url": "^1.2.4",
+        "node-fetch": "^2.6.9",
+        "opencollective-postinstall": "^2.0.3",
+        "regenerator-runtime": "^0.13.3",
+        "tesseract.js-core": "^5.1.0",
+        "wasm-feature-detect": "^1.2.11",
+        "zlibjs": "^0.3.1"
+      }
+    },
+    "node_modules/tesseract.js-core": {
+      "version": "5.1.0",
+      "resolved": "https://registry.npmjs.org/tesseract.js-core/-/tesseract.js-core-5.1.0.tgz",
+      "integrity": "sha512-D4gc5ET1DF/sDayF/eVmHgVGo7nqVC2e3d7uVgVOSAk4NOcmUqvJRTj8etqEmI/2390ZkXCRiDMxTD1RFYyp1g=="
+    },
+    "node_modules/tr46": {
+      "version": "0.0.3",
+      "resolved": "https://registry.npmjs.org/tr46/-/tr46-0.0.3.tgz",
+      "integrity": "sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw=="
+    },
+    "node_modules/wasm-feature-detect": {
+      "version": "1.6.2",
+      "resolved": "https://registry.npmjs.org/wasm-feature-detect/-/wasm-feature-detect-1.6.2.tgz",
+      "integrity": "sha512-4dnaZ+Fq/q+BbMlTIfaNS851i+0zmHzui++NUZdskESRu3xwB6g6x2FnGvBdWtpijqO5yuj1l+EUTJGc4S4DKg=="
+    },
+    "node_modules/webidl-conversions": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/webidl-conversions/-/webidl-conversions-3.0.1.tgz",
+      "integrity": "sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ=="
+    },
+    "node_modules/whatwg-url": {
+      "version": "5.0.0",
+      "resolved": "https://registry.npmjs.org/whatwg-url/-/whatwg-url-5.0.0.tgz",
+      "integrity": "sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==",
+      "dependencies": {
+        "tr46": "~0.0.3",
+        "webidl-conversions": "^3.0.0"
+      }
+    },
+    "node_modules/zlibjs": {
+      "version": "0.3.1",
+      "resolved": "https://registry.npmjs.org/zlibjs/-/zlibjs-0.3.1.tgz",
+      "integrity": "sha512-+J9RrgTKOmlxFSDHo0pI1xM6BLVUv+o0ZT9ANtCxGkjIVCCUdx9alUF8Gm+dGLKbkkkidWIHFDZHDMpfITt4+w==",
+      "engines": {
+        "node": "*"
+      }
+    }
+  }
+}

package.json

@@ -0,0 +1,5 @@
+{
+  "dependencies": {
+    "tesseract.js": "^5.1.0"
+  }
+}

pytesseractJsOCR.js

@@ -0,0 +1,20 @@
+const Tesseract = require('tesseract.js');
+const fs = require('fs');
+
+const image = process.argv[2];
+const lang = process.argv[3];
+const saveFilePath = process.argv[4];
+
+Tesseract.recognize(
+  image,
+  lang,
+  {
+    logger: m => console.log(m)
+  }
+).then(({ data: { text } }) => {
+  console.log(text);
+  fs.writeFileSync(saveFilePath, text);
+}).catch(err => {
+  console.error(err);
+  fs.writeFileSync(saveFilePath, 'Error: ' + err.message);
+});

requirements.txt

@@ -5,4 +5,6 @@ Pillow
 torch
 huggingface-hub
 opencv-python
-numpy
+numpy
+pyppeteer
+playwright