deep learning, machine learning , image processing Assignment | Online Assignment

hello respected sir/madam: attract to my gig if you really feel you can. Actually i want to publish my research paper in SCI index , no matter which impact factor but good impact factor. if some of your paper have been published in SCI index then most welcome. requirement: any new idea related to deep learning , machine learning or image processing that is acceptable for SCI index journal. like skin lesion detection by using deep leaning techniques.. Football events detection events by using machine learning or deep learning etc. and one more this research paper must includes framework , mathematical explanation , algorithms with valid literature review and reference.

Cricket Video Events Recognition using HOG, LBP and Multi-class SVM
Abstract. The world has witnessed a growth in multimedia data, especially video data over the past few years due to increased internet bandwidth and higher processing power of computers. Having a large number of video data also require techniques to store, summarize, index and information retrieval. More attention has been given in recent years to develop techniques which summarize, index and retrieve sports videos due to its commercial aspects. This paper proposes a framework which classifies a cricket video into one of the four events namely Bowled Out, Caught Behind, Catch Out and LBW Out. The framework uses training videos from each category of event and summarizes the videos into key frames. HOG and LBP features are computed for key frames and fused to form a single feature vector which will be labeled accordingly which represents a single event in video. Feature vector is given to a Multi-Class SVM which classifies the video into one of the four events. The experimental results show that the Precision of our technique is 77.23%, Recall is 77.86%, F-Measure is 77.55% and the Accuracy is 65.62%. The evaluation metrics of our technique are promising, because in the literature there is no other technique present so far for event detection & classification in cricket videos.
1. Introduction
The world of multimedia has witnessed exponential growth in video data. Video data has grown in recent years mainly due to improvements in multimedia technology, improved processing power, faster & robust networks and economical storage devices. Improvements in the technology has led to generation of a vast amount of video data, belonging to different areas like movies, sports, surveillance and news etc. [1]. Efficient management of video data is considered as a very challenging task, firstly because video data has a huge size and secondly because of different structure unlike text and audio data.
Due to huge money-making capacity and large number of TV viewership in a game of cricket, the automatic highlights generation is considered to be of utmost importance [3]. Most of the viewers are only interested in watching a compact version of a completed game rather than a full match, which includes most of the exciting parts happen in a complete match. It is evident from the fact that the compact version of a completed match, which contains most of the exciting events, not just saves time of the viewers but also takes less bandwidth while transferring such videos over the internet.
The main contributions of proposed framework are as follows:
 An automatic event detection and classification from cricket video is presented in the proposed framework. The proposed framework is one of a kind, as there is no other technique present in the existing literature which detects and classifies important events from a cricket video. There exist other techniques which are based on cricket videos but they do not explicitly do detect and classify the important events from those videos.
 There does not exist any standard dataset for training and testing of events present in a cricket video. The dataset for this purpose has been manually developed, by separating those clips from a large cricket video which belonged to an event. Thus 160 clips each belonging to four events namely Bowled Out, LBW Out, Caught Behind and Catch Out were created manually.
The rest of the paper is organized as follows. Section 2 of this paper discusses the related work, Section 3 presents the proposed framework, in Section 4 the experimental results are discussed and in Section 5 the paper is concluded.
2. Related Work
In this section we discuss previous research in the field of sport video processing and analysis. In the past few years there has been an extensive research in the field of semantic analysis of sports videos. Automatic sport video annotations, sports video indexing, video retrieval and automatic highlights creation by making use of semantically important sports video content along with multi-model data was focused in the research [4]. Semantic analysis of sports video is considered as a challenging task, the presence of huge amount of sport video, different numbers of sports video broadcasters and existence of semantic gap between the high level and low level features [2]. The existing research in the field of sports video analysis can be broadly divided into two categories genre-specific and genre-independent. Most of the research in the field of semantic analysis of sports video is genre-specific, mainly because every sport is played differently and has different number of rules and actions. Genre-specific research focuses on specific sports video like soccer [2], Baseball [6], Volleyball [7], Tennis, Cricket [3,8], Golf and Basketball. As far as genre-independent work is concerned there has not been an extensive work in this regard. Genre-independent research in the field of semantic analysis of sports video can be found in the research of [7]. For detection of an event in a particular sports video, it is not wise to claim that a genre-independent solution would provide feasible solution because no two sports are the same and every sport has its own set of rules and structure. American Football videos have been summarized by making use of textual overlays present in the videos by [10]. Game stats in textual form are used for generating video abstract in this technique. Li et al. [11] have presented rule-based algorithm to summarize soccer videos, which makes use of aural and video features. It detects replay segments, close-up segments and start of exiting events by using audio and visual information in the video.
Many researchers have also employed machine learning algorithm for sports video analysis. Hidden Markov Model based methodology has been presented by [12] which fused audio and visual features to classify play or break scenes in football videos. This technique only classifies the video scene into two classes which is play or break scene. Event detection in football video by employing SVM has been done in the work of [13]. In this technique goal in a soccer match is detected by first detecting the ball and its position relative to the goal post in a football field. Free kicks, corners and penalty kicks are the three events which are classified by Hidden Markov Model from soccer videos [14]. Bayesian Network, another machine learning technique, has been used by [15] to detect goal event in a sequence of soccer videos. Dynamic Bayesian Network has been used by [16] to detect events like a card given after a foul, corner kick, penalty kick and a goal scored in a soccer video. Audio and visual features both are used for detection of events in this technique.
In this paper we propose a framework which detects and classifies significant events from a cricket video, which are Bowled Out, Catch Out, LBW Out and Catch Out. Our framework is unique in a sense that there is no other technique which exists in the literature which detects and classifies events from a cricket video. There was no standard dataset of cricket videos, so dataset containing events from a large set of cricket videos was created manually by separating video clips containing an event. Each video in the dataset belongs to a particular event and these videos are used for training and testing purposes.
3. Proposed Method
In this section, all the processing steps involved in our proposed framework are explained in detail. Our video dataset Ð is divided into training and testing dataset ÐTraining and ÐTesting, where the dataset Ð consists of video clips from four different types of events i.e., Bowled Out, Catch Out, LBW Out and Caught Behind Out. The training dataset is represented as ÐTraining = {ѴT1, ѴT2, ѴT3…. ѴT 3(N/4)}, and testing dataset is represented as ÐTesting = {ѴT3(N/4) +1 …. ѴTN} where N is the total number of videos in our video dataset Ð. During the training process videos in the training dataset are summarized into five key frames which are extracted for further processing by employing the summarization technique proposed in [19]. For instance, a video ѴiT from our dataset is taken and a set
Figure 1. Proposed Framework for Cricket Event Classification.
Table 1. Description of the symbols used in the proposed framework.
Ð → Video Dataset
Ƒivn HOG → nth frame‟s HOG feature of ith video
ÐTraining→ Training Video Dataset
Ƒiv HOG → HOG features extracted from all five frames of video Ƒiv
ÐTesting → Test Dataset
Ƒiv LBP→ LBP features extracted from all five frames of video Ƒiv
ѴiT →ith video
Ƒivn LBP → nth frame‟s LBP feature of ith video
Ƒiv → Key frames of ith video
( ) → Fused feature vector for frames of all videos
Ƒiv1 → First frame of the ith video
Ĺj → Event labels
Ƒivn → nth frame of the ith video
SVM ç → Multi-class SVM classifier
( )̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅→ Feature vector of key frames in test dataset ÐTesting
of frames are extracted from it Ƒiv = {Ƒiv1, Ƒiv2, …, Ƒivn}, where n = 5 and Ƒiv represents one particular video from the database and Ƒiv1 represents the first frame of the first video. The experimental results show us that five key frames are sufficient for further processing and five key frames represents the entire video clip. Every extracted key frame‟s size is adjusted to 125 by 250, it is converted into grayscale and each image is enhanced by applying Median Filter and Histogram Equalization to remove any noise and blur. In the next step HOG descriptor is used for every key frame and combined to form a HOG feature vector for a single video clip. Then LBP descriptor is used to extract features of all five key frames of the video and combined to form a feature vector. In the next step HOG and LBP feature vectors of all the five key frames of a single video clip are fused to form a single feature vector. In case of Ƒiv which is the set of extracted frames from any video, if HOG is applied on this set of images and combined together then it will be represented as a feature
vector Ƒiv HOG, after applying LBP on the frames we will get its combined feature vector Ƒiv LBP. Once we get the features Ƒiv HOG and Ƒiv LBP, we fuse the two features together to get a single feature vector ( ). Feature vector is computed for all the extracted video frames and they are assigned a label according to the events they belong to as Ĺi = {Ĺ1, … Ĺ4} where i represents all four events. For training purposes these labeled features are given to a multi-class SVM ç. In testing phase a video is given as an input from the training dataset ÐTraining, key frames are extracted from the video and preprocessed, their features are extracted accordingly and represented as ( )̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅̅ and are tested against the their labels Ĺi. The proposed framework is shown in the Figure 1. Details of all the symbols of the framework are shown in Table 1.
3.1. Frame Selection and Pre-processing
In the first step each video ѴiT from ÐTraining is given to the system as an input. If the number of