Question

我正在使用tesseract来检测图像和pdf上的文本。我已经在OSX El Capitan上安装了它并且它的工作非常好。另外我把它安装在Ubuntu 16.04服务器上。但它表现不佳。结果在相同图像上是不同的。它在两个系统上的版本相同：Tesseract 4.00 Alpha，Leptonica 1.74.1

OSX

tesseract 4.00.00alpha
leptonica-1.74.1
libjpeg 8d : libpng 1.6.29 : libtiff 4.0.7 : zlib 1.2.5

Ubuntu的

tesseract 4.00.00alpha
leptonica-1.74.1
libjpeg 8d (libjpeg-turbo 1.4.2) : libpng 1.2.54 : libtiff 4.0.6 : zlib 1.2.8

我正在使用Wand包装器将image / pdf文件转换为python中的jpeg与imagemagick / libmagick-dev。我想这与jpeg编码有关。为什么它表现得那样？

    all_pages = WI(filename=args['image'], resolution=300)
    all_pages.compression_quality = 100
    #i set the compression type but this doesn't changed anything
    #all_pages.compression = 'jpeg2000'
    image_jpeg = all_pages.convert('jpg')

    single_image = WI(image=image_jpeg.sequence[0])
    blob = single_image.make_blob("jpg")

    single_image.close()
    all_pages.close()

    img = PI.open(BytesIO(blob)).convert("L")
    greyImg = np.array(img)
    # do some image processing

    pIm_bw = PI.fromarray(output)      
    builder = pyocr.builders.LineBoxBuilder()
    print("LineBoxBuilder set")
    txt = tool.image_to_string(
        pIm_bw,
        lang=language,
        builder=builder
    )

Tesseract不同的结果

0 个答案: