Automatic Group Happiness Intensity Analysis

Automatic Group Happiness Intensity Analysis

Abstract:

The recent advancement of social media has given users a platform to socially engage and interact with a larger population. Millions of images and videos are being uploaded everyday by users on the web from different events and social gatherings. There is an increasing interest in designing systems capable of understanding human manifestations of emotional attributes and affective displays. As images and videos from social events generally contain multiple subjects, it is an essential step to study these groups of people. In this paper, we study the problem of happiness intensity analysis of a group of people in  an image using facial expression analysis. A user perception study is conducted to understand various attributes, which affect a person’s perception of the happiness intensity of a group. We identify the challenges in developing an automatic mood analysis system and propose three models based on the attributes in the study. An ‘in the wild’ image-based database is collected. To validate the methods, both quantitative and qualitative experiments are performed and applied to the problem of shot selection, event summarisation and album creation. The experiments show that the global and local attributes defined in the paper provide useful information for theme expression analysis, with results close to human perception results.

Algorithm:

1.     Clustering algorithm

·        For take a picture in video

2.     Emotion Detection Algorithm
·        Find smiling face

3.     Spanning tree algorithm
·        Order the picture

Existing System

·        A labelled ‘in the wild’ database containing images of groups of people is collected using a semi-automatic process and compared with existing databases.

·        In the existing literature, the faces are considered independent of each other. For computing the contribution of each subject, two types of factors affect group level emotion analysis.

(1)  Local factors

(2)  Global factors

Disadvantages:

·       In the previous process the time taken for detecting face is too long in windows processed.

Proposed System

·        The proposed frameworks, including both quantitative and qualitative experiments.

·        In another interesting bottom-up method, proposed group classification for recognising urban tribes (a group of people part of a common activity). Low-level features, such as colour histograms, and high-level features, such as age, gender, hair and hat, were used as attributes (using the Face.com API) to learn a Bag-of-Words (BoW)-based classifier.

·        In an interesting top-down approach, [5] proposed contextual features based on the group structure for computing the age and gender of individuals.

Advantages:

·       In the proposed process the time taken for detecting face time only in windows processed.

Modules

1.    Snapshot

2.    Emotion Detection

3.    Comparing

Snapshot

As images and videos from social events generally contain multiple subjects, it is an essential step to study these groups of people. In this paper, we study the problem of happiness intensity analysis of a group of people in an image using facial expression analysis. However, little attention has been given to the estimation of the overall expression theme conveyed by a group of people in an image. The contribution towards the theme expression can be affected by the social context. The context can constitute various global and local factors (such as the relative position of the person in the image, their distance from the camera and the level of face occlusion).

Emotion Detection

Consider an illustrative example of inferring the mood of group of people posing for a group photograph at a school reunion. To scale the current emotion detection algorithms to work on this type of data in the wild, there are several challenges to overcome such as emotion modelling of groups of people, labelled data, and face analysis. Expression  analysis has been a long studied problem, focussing on

inferring the emotional state of a single subject only. This paper discusses the problem of automatic mood analysis of a group of people. Here, we are interested in knowing an individual’s intensity of happiness and its contribution to the overall mood of the scene.

 Comparing

which have an effect on the group members. For example, a group of people laughing at a party displays happiness in a different way than a group of people in an office meeting room. From an image perspective, this means that the scene/background information can be used as affective context. The bottom-up component deals with the subjects in the group in terms of attributes of individuals that affect the perception of the group’s mood. It defines the contribution of individuals to the overall group mood. The presence of occlusion on a face reduces its visibility and, therefore, hampers the clear estimation of facial expressions. It also reduces the face’s contribution to the overall expression intensity of a group portrayed in an image.

HARDWARE & SOFTWARE REQUIREMENTS:

 HARDWARE REQUIREMENTS: 

·                     System                  :         Pentium IV 2.4 GHz.

·                     Hard Disk              :         40 GB.

·                     Floppy Drive         :         1.44 Mb.

·                     Monitor                 :         15 VGA Color.

·                     Mouse                   :         Logitech.

·                     Ram                      :         512 MB.

  SOFTWARE REQUIREMENTS: 

·                     Operating system   :         Windows XP Professional.

·                     Coding Language   :         C#.NET