In the recent yeas, with the increase in the use of different social media platforms, image captioning approach play a major role in automatically describe the whole image into natural language sentence. Image captioning plays a significant role in computer-based society. Image captioning is the process of automatically generating the natural language textual description of the image using artificial intelligence techniques. Computer vision and natural language processing are the key aspect of the image processing system. Convolutional Neural Network (CNN) is a part of computer vision and used object detection and feature extraction and on the other side Natural Language Processing (NLP) techniques help in generating the textual caption of the image. Generating suitable image description by machine is challenging task as it is based upon object detection, location and their semantic relationships in a human understandable language such as English. In this paper our aim to develop an encoder-decoder based hybrid image captioning approach using VGG16, ResNet50 and YOLO. VGG16 and ResNet50 are the pre-trained feature extraction model which are trained on millions of images. YOLO is used for real time object detection. It first extracts the image features using VGG16, ResNet50 and YOLO and concatenate the result in to single file. At last LSTM and BiGRU are used for textual description of the image. Proposed model is evaluated by using BLEU, METEOR and RUGE score.

No abstract

Biometrics recognizes individual basedon the features from their physiological and/or behavioural characteristics. These systems provide reliable recognition schemes for determining the individual identity. Applications of these systems include computer systems security, credit card, access to buildings in a secure way. Using biometric, the person itself is a password. Fusion at the feature level is believed to give better results by incorporating feature vectors which contain richer information which is nonlinear and captures different statistical properties. Therefore, a new feature extraction framework is proposed here from the fusion of face and palmprint biometric. The proposed approach focuses on the development of this new framework for the fusion purpose. This method is able to extract important information in different orientations and scales, and is thus able to capture nonlinear information in different biometric image like face and palmprint etc. The proposed paper shows that integration of face and palmprint biometrics can achieve higher performance that may not be possible using a single biometric indicator alone.Keywords: Biometrics, Multimodal Biometrics, Identification, Security, Verification, Templates, Fusion, Local Feature Extraction.. I. INTRODUCTIONA multimodal biometric authentication recognizes an individual person using physiological and/or behavioral characteristics, such as finger knuckle print, face, fingerprints, hand geometry, iris, retina, vein and speech is one of the most attractive and effective methods. These methods are more reliable and capable than knowledge-based techniques [17] - [24]. Since biometric features are hardly stolen or forgotten. However, a single biometric feature sometimes fails to be exact enough for verifying the identity of a person. By combining multiple modalities enhanced performance reliability could be achieved. Measurable means that the characteristic or trait can be easilypresented to a sensor and converted into a quantifiable,digital format [17] -[24]. This allows for the automated matchingprocess to occur in a matter of seconds.The robustness of a biometric is a measure of the extent towhich the characteristic or trait is subject to significantchanges over time. These changes can occur as a result ofage, injury, illness, occupational use, or chemical exposure.A highly robust biometric does not change significantly overtime. A less robust biometric does. For example, the iris,which changes very little over a person"s lifetime, is morerobust than a voice. Due to its promising applications as well as the theoretical challenges, multimodal biometric has drawn more and more attention in recent years [1]. Face and palmprint multimodal biometrics are advantageous due to the use of non-invasive and low-cost image acquisition. In this method we can easily acquire face and palmprint images using two touchless sensors simultaneously. Existing studies in this approach [2,3] employ holistic features for face representation and results are shown with ...

No abstract