Saturday October 30 10:30 AM – Saturday October 30 12:00 PM in Workshop/Tutorial II

Image(face) Classification with Computer Vision and Python


Prior knowledge:
Previous knowledge expected
computer vision, pandas, Keras, Numpy, DeepLearning


Image recognition (or image classification) is the task of identifying images and categorizing them in one of several predefined distinct classes. So, image recognition software and apps can define what’s depicted in a picture and distinguish one object from another.

The tutorial is aimed at enabling machines with this ability is called computer vision.


The aim of this tutorial is to provide an up-to-date review of computer vision in facial image processing with python, especially in the areas of entertainment industry, surveillance, and other human computer interaction applications. To be more specific, this tutorial reviews and demonstrates the techniques of visible facial analysis.

In computer vision, one essential problem we are trying to figure out is to automatically detect objects in an image without human intervention. Face detection can be thought of as such a problem where we detect human faces in an image. There may be slight differences in the faces of humans but overall, it is safe to say that there are certain features that are associated with all the human faces.

Face detection is usually the first step towards many face-related technologies, such as face recognition or verification. However, face detection can have very useful applications. The most successful application of face detection would probably be photo taking. When you take a photo of your friends, the face detection algorithm built into your digital camera detects where the faces are and adjusts the focus accordingly. The face is a major aspect of the human body that is used for recognition and aids in the transfer of information or communication, as well as the interpretation and comprehension of emotions.

A great deal of information has been gleaned from facial photographs.

age, emotion, color, gender, and other factors

All of this information, as well as the recognition of a

The human brain effortlessly processes people, yet a

a problem in the field of computer vision

Regardless of the many applications of several,

Applications of biometrics Variations in this regard include:

occlusion, stance, illumination, and emotion are all frequent in photography.

reasons why face recognition is still a problem in the workplace

Artificial Intelligence, Computer Vision, and a variety of other domains

extra information. There are primarily two Face uses.

Identification and verification are two types of recognition. These

Images can be manipulated in a variety of ways thanks to software.

By the extraction of discriminative information, it was categorised and identified.

characteristics extracted from the photographs These are the applications that are used as the

phase of pre-processing for dimensionality reduction and noise reduction

[35] Cleaning and information packaging Identification of the person's face

can be thought of as a method for recognizing a person's face.

The detection and identification of an object is fed back to the system.

While face verification, a human in a facial image input

is based on the foundation of a computational effort completed by

The face image input is used in the identification procedure. It

As a result, a facial recognition system is used to verify the information.

To determine whether a person's identity is true or false. As a result,

the requirement that every pattern matching be exact with a

The system saves each individual's stated and desired output.

Each time a person is photographed, data about their face characteristics is entered into a database.

In an image, you've been labeled. As a result, enough information is required.

acquired in such a way that the data can be used to distinguish a

Several images show a similar face. It is suggested that you label everything.

those photos with people's or a person's name on them

Face recognition has also become more common in computers.

There is a lot of variation in the recognition problem.

age, illumination, facial expression, head movement and tilt

intensity, angle, and so forth. Several attempts at face expressions

Machine recognition has enabled for little or no human intervention.

These quantities have a lot of variation. Nonetheless, the patterning process

unprocessed optical data matching, which is commonly employed

When there's a lot of variation, it's almost certain to fail.