91成人手机在线,日日夜夜免费看三级片,狠狠狠狠狠狠狠操,亚洲男人网站,日韩操逼,久久偷拍片久久,中文字幕无码电影,伊人成人在线

目錄：AIAS - AI加速器

文字識(shí)別（OCR）目前在多個(gè)行業(yè)中得到了廣泛應(yīng)用，比如金融行業(yè)的單據(jù)識(shí)別輸入，餐飲行業(yè)中的發(fā)票識(shí)別，交通領(lǐng)域的車(chē)票識(shí)別，企業(yè)中各種表單識(shí)別，以及日常工作生活中常用的身份證，駕駛證，護(hù)照識(shí)別等等。 OCR（文字識(shí)別）是目前常用的一種AI能力。

OCR工具箱功能:

方向檢測(cè)，支持4個(gè)文字方向：0度、90度、180度、270度。

2. 圖片旋轉(zhuǎn)
3. 文字識(shí)別，提供三個(gè)模型：mobile模型，light模型，服務(wù)器端大模型。
4. 版面分析（支持5個(gè)類(lèi)別, 用于配合文字識(shí)別，表格識(shí)別的流水線(xiàn)處理）
Text，Title，List，Table，F(xiàn)igure
5. 表格識(shí)別

生成html表格
生成excel文件

運(yùn)行OCR識(shí)別例子

1.1 文字方向檢測(cè)：

例子代碼: OcrDetectionExample.java
運(yùn)行成功后，命令行應(yīng)該看到下面的信息:

[INFO ] - Result image has been saved in: build/output/detect_result.png
[INFO ] - [
	class: "0", probability: 1.00000, bounds: [x=0.073, y=0.069, width=0.275, height=0.026]
	class: "0", probability: 1.00000, bounds: [x=0.652, y=0.158, width=0.222, height=0.040]
	class: "0", probability: 1.00000, bounds: [x=0.143, y=0.252, width=0.144, height=0.026]
	class: "0", probability: 1.00000, bounds: [x=0.628, y=0.328, width=0.168, height=0.026]
	class: "0", probability: 1.00000, bounds: [x=0.064, y=0.330, width=0.450, height=0.023]
]

輸出圖片效果如下：

1.2 文字方向檢測(cè)幫助類(lèi)（增加置信度信息顯示，便于調(diào)試）：

例子代碼: OcrDetectionHelperExample.java
運(yùn)行成功后，命令行應(yīng)該看到下面的信息:

[INFO ] - Result image has been saved in: build/output/detect_result_helper.png
[INFO ] - [
	class: "0 :1.0", probability: 1.00000, bounds: [x=0.073, y=0.069, width=0.275, height=0.026]
	class: "0 :1.0", probability: 1.00000, bounds: [x=0.652, y=0.158, width=0.222, height=0.040]
	class: "0 :1.0", probability: 1.00000, bounds: [x=0.143, y=0.252, width=0.144, height=0.026]
	class: "0 :1.0", probability: 1.00000, bounds: [x=0.628, y=0.328, width=0.168, height=0.026]
	class: "0 :1.0", probability: 1.00000, bounds: [x=0.064, y=0.330, width=0.450, height=0.023]
]

輸出圖片效果如下：

2. 圖片旋轉(zhuǎn)：

每調(diào)用一次rotateImg方法，會(huì)使圖片逆時(shí)針旋轉(zhuǎn)90度。

例子代碼: RotationExample.java

3. 文字識(shí)別：

再使用本方法前，請(qǐng)調(diào)用上述方法使圖片文字呈水平(0度)方向。

例子代碼: LightOcrRecognitionExample.java
運(yùn)行成功

后，命令行應(yīng)該看到下面的信息:

[INFO ] - [
	class: "你", probability: -1.0e+00, bounds: [x=0.319, y=0.164, width=0.050, height=0.057]
	class: "永遠(yuǎn)都", probability: -1.0e+00, bounds: [x=0.329, y=0.349, width=0.206, height=0.044]
	class: "無(wú)法叫醒一個(gè)", probability: -1.0e+00, bounds: [x=0.328, y=0.526, width=0.461, height=0.044]
	class: "裝睡的人", probability: -1.0e+00, bounds: [x=0.330, y=0.708, width=0.294, height=0.043]
]

輸出圖片效果如下：

4. 版面分析：

運(yùn)行成功后，命令行應(yīng)該看到下面的信息:

[INFO ] - [
	class: "Text", probability: 0.98750, bounds: [x=0.081, y=0.620, width=0.388, height=0.183]
	class: "Text", probability: 0.98698, bounds: [x=0.503, y=0.464, width=0.388, height=0.167]
	class: "Text", probability: 0.98333, bounds: [x=0.081, y=0.465, width=0.387, height=0.121]
	class: "Figure", probability: 0.97186, bounds: [x=0.074, y=0.091, width=0.815, height=0.304]
	class: "Table", probability: 0.96995, bounds: [x=0.506, y=0.712, width=0.382, height=0.143]
]

輸出圖片效果如下：

5. 表格識(shí)別：

運(yùn)行成功后，命令行應(yīng)該看到下面的信息:


 
  
...
   
   
    
     Methods
     R
     P
     F
     FPS
    
   
   
    
     SegLink[26]
     70.0
     86.0
     770
     89
    
    
     PixelLink[4j
     73.2
     83.0
     77.8