Golang : Apply Histogram Equalization to color images
For this tutorial, we will learn how to convert color images to greyscale and then apply Histogram Equalization as a way to standardize the brightness and contrast. This is a step to pre-process the image for facial recognition purpose with Eigenface method.
An example output. Left most is the original and right most image is the final product.
Here you go!
package main
import (
"fmt"
"github.com/lazywei/go-opencv/opencv"
"image"
gif "image/gif"
_ "image/jpeg"
_ "image/png"
"net/http"
"os"
)
func errCheck(err error) {
if err != nil {
panic(err)
}
}
func main() {
if len(os.Args) != 2 {
fmt.Printf("Usage : %s <imagefilename>\n", os.Args[0])
os.Exit(0)
}
imageFileName := os.Args[1]
// we will use Go's method of load images
// instead of openCV.LoadImage
// because we want to detect if the user supplies animated GIF or not
imageFile, err := os.Open(imageFileName)
errCheck(err)
defer imageFile.Close()
img, _, err := image.Decode(imageFile)
errCheck(err)
buffer := make([]byte, 512)
imageFile.Seek(0, 0) // reset reader
_, err = imageFile.Read(buffer)
errCheck(err)
filetype := http.DetectContentType(buffer)
// check if image is GIF and if yes, check to see if it is animated GIF by
// counting the LoopCount number
fmt.Println("Analyzing image type : ", filetype)
if filetype == "image/gif" {
imageFile.Seek(0, 0)
// warn if image is animated GIF
gif, err := gif.DecodeAll(imageFile)
errCheck(err)
if gif.LoopCount != 0 {
fmt.Println("Animated gif detected. Will only scan for faces in the 1st frame.")
}
}
// convert Go's image.Image type to OpenCV's IplImage(Intel Image Processing Library)
openCVImg := opencv.FromImage(img)
defer openCVImg.Release()
if openCVImg != nil {
fmt.Println("Converting [" + imageFileName + "] to greyscale image......")
w := openCVImg.Width()
h := openCVImg.Height()
// create an IplImage with 1 channel(grey)
greyImg := opencv.CreateImage(w, h, opencv.IPL_DEPTH_8U, 1)
defer greyImg.Release()
// convert to greyscale
opencv.CvtColor(openCVImg, greyImg, opencv.CV_BGR2GRAY)
// from http://www.shervinemami.info/faceRecognition.html
// make the image a fixed size
// CV_INTER_CUBIC or CV_INTER_LINEAR is good for enlarging, and
// CV_INTER_AREA is good for shrinking / decimation, but bad at enlarging.
histoEqImg := opencv.CreateImage(w, h, opencv.IPL_DEPTH_8U, 1)
defer histoEqImg.Release()
histoEqImg = opencv.Resize(greyImg, w, h, opencv.CV_INTER_LINEAR)
fmt.Println("Applying Histogram Equalization to [" + imageFileName + "]......")
// standard brightness and contrast
greyImg.EqualizeHist(histoEqImg)
// save to file
fmt.Println("Saving results to [grey.jpg] and [equalhisto.jpg]")
opencv.SaveImage("./grey.jpg", greyImg, opencv.CV_IMWRITE_JPEG_QUALITY)
opencv.SaveImage("./equalhisto.jpg", histoEqImg, opencv.CV_IMWRITE_JPEG_QUALITY)
} else {
panic("OpenCV FromImage error")
}
}
Happy coding and recognizing face with computer vision!
References:
http://www.shervinemami.info/faceRecognition.html
http://docs.opencv.org/2.4/modules/contrib/doc/facerec/facerec_tutorial.html
See also : Golang : GUI with Qt and OpenCV to capture image from camera
By Adam Ng
IF you gain some knowledge or the information here solved your programming problem. Please consider donating to the less fortunate or some charities that you like. Apart from donation, planting trees, volunteering or reducing your carbon footprint will be great too.
Advertisement
Tutorials
+17.8k Golang : How to run your code only once with sync.Once object
+2.9k Golang : PGX CopyFrom to insert rows into Postgres database
+12k Golang : Convert(cast) int to int64
+10.7k Golang : Simple client-server HMAC authentication without SSL example
+30.8k Golang : Convert []string to []byte examples
+11.4k Golang : Get terminal width and height example
+5.4k Unix/Linux : Use netstat to find out IP addresses served by your website server
+3.9k Google : Block or disable caching of your website content
+7.1k Your page has meta tags in the body instead of the head
+6.9k Golang : Get final or effective URL with Request.URL example
+20k Golang : Upload big file (larger than 100MB) to AWS S3 with multipart upload
+9.7k Golang : Generate random elements without repetition or duplicate