Imane Hachchane

Bio: Imane Hachchane is an academic researcher from University of Hassan II Casablanca. The author has contributed to research in topics: Object detection & Relevance (information retrieval). The author has an hindex of 2, co-authored 3 publications receiving 8 citations.

Large-scale image-to-video face retrieval with convolutional neural network features

Abstract: Convolutional neural network features are becoming the norm in instance retrieval. This work investigates the relevance of using an of the shelf object detection network, like Faster R-CNN, as a feature extractor for an image-to-video face retrieval pipeline instead of using hand-crafted features. We use the objects proposals learned by a Region Proposal Network (RPN) and their associated representations taken from a CNN for the filtering and the re-ranking steps. Moreover, we study the relevance of features from a finetuned network. In addition to that we explore the use of face detection, fisher vector and bag of visual words with those CNN features. We also test the impact of different similarity metrics. The results obtained are very promising.

New Faster R-CNN Neuronal Approach for Face Retrieval

Abstract: Image features acquired from pre-entrained convolutional neural networks (CNN) are becoming the norm in instance retrieval. This work investigates the relevance of using an object detection CNN like Faster R-CNN as a feature extractor. We built a face retrieval pipeline composed of filtering and re-ranking that uses the objects proposals learned by a Region Proposal Network (RPN) and their associated representations taken from a CNN. Moreover, we study the relevance of Faster R-CNN representations when the network is fine-tuned for the same data that we want to recover. We evaluate the performance of the system with the Labeled Faces in the Wild (LFW) database 13k, the FERET database 3K, and Faces94 database 2k. The results obtained are very encouraging.

Video Retrieval Using Query Images and CNN Features

Abstract: We address the problem of image-to-video face retrieval. Given a query image of a person, the aim is to retrieve videos of that same person. The methods proposed so far are based on hand-crafted features. In this work we investigate the use of an off-the-shelf object detection network as a feature extractor by building an image-to-video face retrieval pipeline composed of an offline feature extractor and online filtering and re-ranking steps that use the object proposals learned by a Region Proposal Network (RPN) and their associated representations taken from a CNN. Moreover we study the relevance of features from a fine-tuned network. In addition to that we explore the use of face detection before extracting the features and we test the impact of different similarity metrics. The results obtained are promising.

Classification of tomato leaf diseases using MobileNet v2

Abstract: Tomato is a red-colored edible fruit originated from the American continent. There are a lot of plant diseases associated with tomatoes such as leaf mold, late blight, and mosaic virus. Tomato is an important vegetable crop that contributes to the world economically. Despite tremendous efforts in plant management, viral diseases are notoriously difficult to control and eradicate completely. Thus, accurate and faster detection of plant diseases is needed to mitigate the problem at the early stage. A computer vision approach is proposed to identify the disease by capturing the leaf images and detect the possibility of the diseases. A deep learning classifier is utilized to make a robust decision that covers a wide variety of leaf appearances. Compact deep learning architecture, which is MobileNet V2 has been fine-tuned to detect three types of tomato diseases. The algorithm is tested on 4,671 images from PlantVillage dataset. The results show that MobileNet V2 is able to detect the disease up to more than 90% accuracy.

Effect of data-augmentation on fine-tuned CNN model performance

Abstract: During the last few years, deep learning achieved remarkable results in the field of machine learning when used for computer vision tasks. Among many of its architectures, deep neural network-based architecture known as convolutional neural networks are recently used widely for image detection and classification. Although it is a great tool for computer vision tasks, it demands a large amount of training data to yield high performance. In this paper, the data augmentation method is proposed to overcome the challenges faced due to a lack of insufficient training data. To analyze the effect of data augmentation, the proposed method uses two convolutional neural network architectures. To minimize the training time without compromising accuracy, models are built by fine-tuning pre-trained networks VGG16 and ResNet50. To evaluate the performance of the models, loss functions and accuracies are used. Proposed models are constructed using Keras deep learning framework and models are trained on a custom dataset created from Kaggle CAT vs DOG database. Experimental results showed that both the models achieved better test accuracy when data augmentation is employed, and model constructed using ResNet50 outperformed VGG16 based model with a test accuracy of 90% with data augmentation & 82% without data augmentation.

Best neural simultaneous approximation

Abstract: For many years, approximation concepts has been investigated in view of neural networks for the several applications of the two topics. Researchers studied simultaneous approximation in the 2-normed space and proved essential theorems concern with existence, uniqueness and degree of best approximation. Here, we define a new 2-norm in Lp -space, with p<1, so we call it Lp quasi 2- normed space (Lp,2) . The set of approximations is a space of feedforward neural networks that is constructed in this paper. Existence and uniqueness of best neural approximation for a function from is proved, describing the rate of best approximation in terms of modulus of smoothness.

Large-scale image-to-video face retrieval with convolutional neural network features

Abstract: Convolutional neural network features are becoming the norm in instance retrieval. This work investigates the relevance of using an of the shelf object detection network, like Faster R-CNN, as a feature extractor for an image-to-video face retrieval pipeline instead of using hand-crafted features. We use the objects proposals learned by a Region Proposal Network (RPN) and their associated representations taken from a CNN for the filtering and the re-ranking steps. Moreover, we study the relevance of features from a finetuned network. In addition to that we explore the use of face detection, fisher vector and bag of visual words with those CNN features. We also test the impact of different similarity metrics. The results obtained are very promising.

The effect of optimizers in fingerprint classification model utilizing deep learning

Abstract: Fingerprint is the most popular way to identify persons, it is assumed a unique identity, which enable us to return the record of specific person through his fingerprint, and could be useful in many applications; such as military applications, social applications, criminal applications… etc. In this paper, the study of a new model based deep learning is suggested. The focus is directed on how to enhance the training model with the increase of the testing accuracy by applying four scenarios and comparing among them. The effects of two dedicated optimizers are shown and their contrast enhancement is tested. The results prove that the testing accuracy is 85.61% for “Adadelta” optimizer, whereas for “Adam” optimizer, it is 91.73%.