# 欢迎！
如果说你看到了这里，那么有两种可能，要么是为 ImageMagic 而来，要么就是闲逛，不过，这里都欢迎你的到来！
# 获取 ImageMagic
- 使用 pip 下载：
pip install ImageMagic |
- 从源进行构建：源
# DOCS
感谢使用 ImageMagic，这是 Python 的第三方库 ImageMagic 的临时文档，请查阅。若在使用过程中有什么问题或是你觉得可以改进的地方，请联系我！
# Image 模块
# word_to_image()
将文本转换成图片
from ImageMagic import Image | |
Image.word_to_image('这里是你要转成图片的文本','F:/image/1.png',fontPath='F:/ttf/字语时光体.ttf') |
# voice_to_word()
识别音频里的内容，使用讯飞的语音转写，你需要去点击这里获取你的 appid 以及 key，支持格式为 WAV, FLAC, OPUS, M4A, MP3
from ImageMagic import Image | |
appid = "" | |
key = "" | |
filepath = "F:/mp3/test.mp3" | |
audio = Image.Audio(appid,key,filepath) | |
text = audio.voice_to_word() | |
print(text) |
# audio_to_image()
将音频内容转为图片，同样，你需要去点击这里获取你的 appid 以及 key，支持格式为 WAV, FLAC, OPUS, M4A, MP3
from ImageMagic import Image | |
appid = "" | |
key = "" | |
filepath = "F:/mp3/test.mp3" | |
Image.audio_to_image(appid,key,filepath,'F:/image/test.png') #最后一个参数是图片保存地址 |
# categorize_image()
分类文件夹里的图片，格式包括 jpg, jpeg, png, webp, bmp, tif, tiff, gif, svg, wmf，会在此文件夹下生成以已有文件的后缀为名的新文件夹，并将同类文件复制到里面
from ImageMagic import Image | |
Image.categorize_image('F:/images') #这里输入你的文件夹路径 |
# convert()
转换图片格式
from ImageMagic import Image | |
Image.convert('F:/image/test.png','webp','F:/image/test.webp') #第一个参数是原文件路径，第二个是转换的格式，第三个是保存路径 |
# equal_scale_image()
将图片等比例缩小或者放大
from ImageMagic import Image | |
Image.equal_scale_image('F:/image/test.png','F:/image/save.png',2) #最后一个参数是变化倍数 |
# customize_image()
自定义修改图片分辨率，若是不输入第三和四个参数，那么将会使用原参数
from ImageMagic import Image | |
Image.customize_image('F:/image/test.png','F:/image/save.png',1960,1080) |
# lbp_image_hash()
哈希局部二值算法计算图片哈希值
from ImageMagic import Image | |
hash = Image.lbp_image_hash('F:/image/test.png') | |
print(hash) |
# p_image_hash()
感知哈希算法计算图片哈希值
from ImageMagic import Image | |
hash = Image.p_image_hash('F:/image/test.png') | |
print(hash) |
# pca_image_hash()
主成分分析算法计算图片哈希值
from ImageMagic import Image | |
hash = Image.pca_image_hash('F:/image/test.png') |
# fft_image_hash()
傅里叶变换算法计算哈希值
from ImageMagic import Image | |
hash = Image.fft_image_hash('F:/image/test.png') |
# average_image_hash()
哈希平均算法计算图片哈希值
from ImageMagic import Image | |
hash = Image.average_image_hash('F:/image/test.png') | |
print(hash) |
# remove_same_images()
删除某目录下相同的图片且每张图片保留一张。
具体实现：通过计算图片的哈希值，相同图片则会被删除。
from ImageMagic import Image | |
Image.remove_same_images('F:/image') |
# Aocr 模块
使用本模块请前往点击这里下载 OCR 引擎
# image_to_text()
识别图像中的文本，参数 filePath：图片路径，lang：图片里的语言，默认中文，可以多语言，例：'chi_sim+eng',timeout: 识别超时时间，默认 0，即无
from ImageMagic import Aocr | |
text = Aocr.image_to_text('F:/image/test.png') |
# image_to_pdf()
将图片转为可搜索的 pdf 文件
from ImageMagic import Aocr | |
Aocr.image_to_pdf('F:/image/test.png','F:/pdf/test.pdf') |
# image_to_hocr()
将图片转为 HOCR
from ImageMagic import Aocr | |
hocr = Aocr.image_to_hocr('F:/image/test,png') |
# image_to_AltoXml()
将图片转为 AltXml
from ImageMagic import Aocr | |
xml = Aocr.image_to_AltoXml('F:/image/test.png') |
# get_image_data()
获取图片详细的数据，包括框、置信度、行号和页码。需要 tesseract 版本 3.05+
from ImageMagic import Aocr | |
data = Aocr.get_image_data('F:/image/test.png') |
# get_image_osd()
获取有关方向和脚本检测的信息
from ImageMagic import Aocr | |
osd = Aocr.get_image_osd('F:/image/test.png') |
# get_image_boxs()
获取图片边界框的估计值
from ImageMagic import Aocr | |
boxs = Aocr.get_image_boxs('F:/image/test.png') |
# check_languages()
获取已安装的语言包
from ImageMagic import Aocr | |
lang = Aocr.check_languages() | |
print(lang) |
# Welcome to you !
If you see it, there are two possibilities, either for ImageMagic or just hanging out, but you're welcome here!
# Where to get it ?
- Download using pip:
pip install ImageMagic |
- Build from source:source
# DOCS
Thanks for using ImageMagic, which is temporary documentation for Python's third-party library ImageMagic, check it out. If there are any problems during use or what you think can be improved, please contact me!
# Image module
# word_to_image()
Convert text to images
from ImageMagic import Image | |
Image.word_to_image("Here's the text you want to turn into an image.",'F:/image/1.png',fontPath='F:/ttf/test.ttf') |
# voice_to_word()
To identify the content in the audio and use iFLYTEK's voice transcription, you need to go to [click here] (https://console.xfyun.cn/services/lfasr) to get your appid and key, which are supported in WAV, FLAC, OPUS, M4A, MP3.
from ImageMagic import Image | |
appid = "" | |
key = "" | |
filepath = "F:/mp3/test.mp3" | |
audio = Image.Audio(appid,key,filepath) | |
text = audio.voice_to_word() | |
print(text) |
# audio_to_image()
To convert audio content to images, you need to go to [click here] (https://console.xfyun.cn/services/lfasr) to get your appid and key, which are supported in WAV, FLAC, OPUS, M4A, MP3.
from ImageMagic import Image | |
appid = "" | |
key = "" | |
filepath = "F:/mp3/test.mp3" | |
Image.audio_to_image(appid,key,filepath,'F:/image/test.png') #The last parameter is the address where the image is saved. |
# categorize_image()
The images in the category folder, including jpg, jpeg, png, webp, bmp, tif, tiff, gif, svg, wmf, will generate a new folder named with the suffix of the existing file under this folder, and copy the same kind of files into it.
from ImageMagic import Image | |
Image.categorize_image('F:/images') #Enter your folder path here |
# convert()
Convert image format.
from ImageMagic import Image | |
Image.convert('F:/image/test.png','webp','F:/image/test.webp') #The first parameter is the path to the original file, the second is the converted format, and the third is the saved path. |
# equal_scale_image()
Reduce or enlarge the image at equal scale.
from ImageMagic import Image | |
Image.equal_scale_image('F:/image/test.png','F:/image/save.png',2) #The last parameter is the multiplier. |
# customize_image()
Customize the image resolution, if you do not enter the third and fourth parameters, the original parameters will be used.
from ImageMagic import Image | |
Image.customize_image('F:/image/test.png','F:/image/save.png',1960,1080) |
# lbp_image_hash()
The hash local binary algorithm calculates the image hash value.
from ImageMagic import Image | |
hash = Image.lbp_image_hash('F:/image/test.png') | |
print(hash) |
# p_image_hash()
The hash awareness algorithm calculates the image hash value.
from ImageMagic import Image | |
hash = Image.p_image_hash('F:/image/test.png') | |
print(hash) |
# pca_image_hash()
The principal component analysis algorithm calculates the image hash value.
from ImageMagic import Image | |
hash = Image.pca_image_hash('F:/image/test.png') |
# fft_image_hash()
The Fourier transform algorithm computes the hash value.
from ImageMagic import Image | |
hash = Image.fft_image_hash('F:/image/test.png') |
# average_image_hash()
The hash averaging algorithm calculates the image hash value.
from ImageMagic import Image | |
hash = Image.average_image_hash('F:/image/test.png') | |
print(hash) |
# remove_same_images()
Delete the same images in a directory and keep one image per image.
Implementation: By calculating the hash value of the image, the same image will be deleted.
from ImageMagic import Image | |
Image.remove_same_images('F:/image') |
# Aocr module
To use this module, go to [click here] (https://tesseract-ocr.github.io/tessdoc/Installation.html) to download the OCR engine.
# image_to_text()
Identify text in an image, parameters filePath: image path, lang: language in the image, default Chinese, can be multilingual, for example: 'chi_sim+eng', timeout: recognition timeout, default 0, that is, none.
from ImageMagic import Aocr | |
text = Aocr.image_to_text('F:/image/test.png') |
# image_to_pdf()
Turn images into searchable PDF files.
from ImageMagic import Aocr | |
Aocr.image_to_pdf('F:/image/test.png','F:/pdf/test.pdf') |
# image_to_hocr()
Turn the picture into HOCR.
from ImageMagic import Aocr | |
hocr = Aocr.image_to_hocr('F:/image/test,png') |
# image_to_AltoXml()
Convert the image to AltXml.
from ImageMagic import Aocr | |
xml = Aocr.image_to_AltoXml('F:/image/test.png') |
# get_image_data()
Get detailed data for an image, including boxes, confidence, line numbers, and page numbers. Requires tesseract version 3.05+.
from ImageMagic import Aocr | |
data = Aocr.get_image_data('F:/image/test.png') |
# get_image_osd()
Get information about orientation and script detection.
from ImageMagic import Aocr | |
osd = Aocr.get_image_osd('F:/image/test.png') |
# get_image_boxs()
Gets an estimate of the picture bounding box.
from ImageMagic import Aocr | |
boxs = Aocr.get_image_boxs('F:/image/test.png') |
# check_languages()
Gets the installed language packs.
from ImageMagic import Aocr | |
lang = Aocr.check_languages() | |
print(lang) |
