What is Digital ImageWhat is Digital Imageprocessing?processing?

An image can be defined as a two-dimensional function, f(x,y) # x and y are spatial (plane) coordinates # The function value f at any pair of coordinates (x,y) is called the intensity, or gray scale of the image # When x, y and the values of f are all finite, discrete quantities, we call the image a digital image # A digital image is composed of a finite number of elements called picture (image) elements, pels, and pixels

•DIP refers to processing digital images by means of a digital computer.• The definition of image processing to be a discipline in which both input and output of a process are images is too limiting• Close relationship to computer vision (close to AI), which aims to emulate human vision

APPLICATIONSAPPLICATIONS

Hollywood film makers use novel Hollywood film makers use novel morphing technologies to generate special morphing technologies to generate special effectseffects

Disney uses morphing to speed up the Disney uses morphing to speed up the production of cartoons production of cartoons

Face morphing

Procedures adoptedProcedures adopted

Pre-processing:Pre-processing:

When getting an image containing human faces, it is always better to do some pre-processing such like removing the noisy backgrounds, clipping to get a proper facial image, and scaling the image to a reasonable size.

Noise reductionNoise reduction

Features finding:Features finding:

4 major feature points, namely the two 4 major feature points, namely the two eyes, and the two endpoints of the eyes, and the two endpoints of the mouth. Within the scope of this project, mouth. Within the scope of this project, we developed an eye-finding algorithm we developed an eye-finding algorithm that successfully detects eyes at 84% that successfully detects eyes at 84% rate.rate.

Eye findingEye finding

Mouth finding

After finding the eyes, we can specify the mouth as After finding the eyes, we can specify the mouth as the red-most region below the eyes.  The red-ness the red-most region below the eyes.  The red-ness function is given by function is given by

Redness = ( R > G * 1.2 ? ) * ( R > Rth ? ) *  { R / (G + Redness = ( R > G * 1.2 ? ) * ( R > Rth ? ) *  { R / (G + epsilon ) } epsilon ) }

where Rth is a threshold, and epsilon is a small where Rth is a threshold, and epsilon is a small number for avoiding division by zero.  number for avoiding division by zero. 

   

Image Partitioning Image Partitioning

# The edges of the face also need to be carefully # The edges of the face also need to be carefully considered in the morphing algorithm.  considered in the morphing algorithm.  # If the face edges do not match well in the # If the face edges do not match well in the morphing process, the morphed image will look morphing process, the morphed image will look strange on the face edges. strange on the face edges. # We generate 6 more feature points around the # We generate 6 more feature points around the face edge, which are the intersection points of face edge, which are the intersection points of the extension line of the first 4 facial feature the extension line of the first 4 facial feature points with the face edges. points with the face edges. 

Demonstration of morphing processDemonstration of morphing process

1.1. Original images scaled to same sizeOriginal images scaled to same size

2. Performing coordinate transformations on 2. Performing coordinate transformations on the partitioned images to match the the partitioned images to match the feature points of these two images.feature points of these two images.

3. Cross-dissolving the two images to 3. Cross-dissolving the two images to generate a new image. generate a new image.

Recent evolutionsRecent evolutions

(1)Morphing between the faces of different (1)Morphing between the faces of different people.people.

(2) Morphing between differentimages of the same person

ConclusionConclusion

An automatic face morphing

algorithm is proposed. The algorithm

consists of a feature finder followed by a

face-morphed that utilizes affine and

bilinear coordinate transforms.

Feature extraction is the key technique toward

building entirely automatic face morphing algorithms.

eyes are the most important features of

human faces. Therefore, in this project we

developed an eye finder based on the idea

that eyes are, generally speaking, more

complicated than the rest of the face.We demonstrated that a hybrid image of two

human faces can be generated by morphing, and

the hybrid face we generated indeed resembles

each of the two "parent" faces.

QUERIES???QUERIES???

Thank you…..Thank you…..