DTI 516 Multimedia Processing

Course description:

Concepts of processing multimedia data; audio; image; video; digital multimedia; interactive multimedia; sampling and signal representation; standards for multimedia coding; compression; filtering; transformation; content analysis; multimedia retrieval; related tools and applications

Download slides

Download Worksheets

Resources

Download OpenCV 3.0 for Windows, (For Mac or Linux)

Python2.7(64bit)+OpenCV3.1

bitmap.txt

small.jpg

star.jpg

lena512color.tiff

frontier_color57.jpg

histogram_dataset.zip

image_dataset1.zip

template.mat

Unequalized_Hawkes_Bay_NZ.jpg

match2_1.tiff

match2_2.tiff

image1.mat

hilow.png

noise1.bmp

noise2.bmp

noise3.bmp

Pavlovsk_Railing_of_bridge_Yellow_palace_Winter.jpg

Valve_original_.PNG

letter.bmp

Plasma.jpg

otsu1.jpg

otsu2.jpg

crack.jpg

coins.jpg

cameraman.tif

solarwind.bmp

tomato.jpg

orange.jpg

led.jpg

highway.jpg

cloud.jpg

cat.jpg

JPEG Quantization tables

lab7_2.mat

jpeg_image.mat

jpeg_image2.mat (512 x 512 pixel)

LV2016.jpg

faces.zip

haarcascade_frontalface_alt.xml

subject02.happy.png

javacv_core.zip

face_demo.txt

Java OCR Example code

Python OCR

OCR Test Image

Python3.6 + Libraries

mahotas-1.4.3-cp36-cp36m-win32.whl

tesseract-ocr-w32

boke.bmp

frame1.bmp

frame2.bmp

frame3.bmp

ladybug.bmp

pan.mp4

pan2.mp4

traverse.mp4

walking.mp4

OCR test image (template)

OCR test image (query1)

OCR test image (query2)

OCR test image (query3)

OCR test image (scan 1)

OCR test image (scan 2)

Source code

Otsu normal method

Otsu faster method

Javacode for imshow function

Zigzag function for entropy encoding

Zigzag function for entropy encoding (python3)

Inverse function for zigzag

Run length encoding function