Deep learning (DL) algorithms have already proved their effectiveness on a wide variety of application domains, including speech recognition, natural language processing, and image classification. To foster their pervasive adoption in applications where low latency, privacy issues and data bandwidth are paramount, the current trend is to perform inference tasks at the edge. This requires deployment of DL algorithms on low-energy and resource-constrained computing nodes, often heterogenous and parallel, that are usually more complex to program and to manage without adequate support and experience. In this paper, we present ALOHA, an integrated tool flow that tries to facilitate the design of DL applications and their porting on embedded heterogenous architectures. The proposed tool flow aims at automating different design steps and reducing development costs. ALOHA considers hardware-related variables and security, power efficiency, and adaptivity aspects during the whole development process, from pre-training hyperparameter optimization and algorithm configuration to deployment.

The handwritten signature is perhaps the most accustomed way for the acknowledgement of the consent of an individual or the authentication of the identity of a person in numerous transactions. In addition, the authenticity of a questioned offline or static handwritten signature still poses a case of interest, especially in forensic related applications. A common approach in offline signature verification system is to apply several predetermined image analysis models. Consequently, any offline signature sample which originates from either authentic persons or forgers, utilizes a fixed feature extraction base. In this proposed study, the feature space and the corresponding projection values depend on the training samples only; thus the proposed method can be found useful in forensic cases. In order to do so, we reenter a groundbreaking unsupervised learning method named archetypal analysis, which is connected to effective data analysis approaches such as sparse coding. Due to the fact that until recently there was no efficient implementation publicly available, archetypal analysis had only few cases of use. However, a fast optimization scheme using an active set strategy is now available. The main goal of this work is to introduce archetypal analysis for offline signature verification. The output of the archetypal analysis of few reference samples is a set of archetypes which are used to form the base of the feature space. Then, given a set of archetypes and a signature sample under examination archetypal analysis and average pooling provides the corresponding features. The promising performance of the proposed approach is demonstrated with the use of an evaluation method which employs the popular CEDAR and MCYT75 signature datasets.

Indirect Immunofluorescence (IIF) followed by manual evaluation of the acquired slides from specialized personnel is the preferred laboratory technique used for the detection of Antinucleolar Antibodies (ANAs) in patient serum. In this procedure, several limitations appear and thus several automatic techniques have been proposed for the task of ANA detection. In this paper we propose a system for automatic classification of HEp-2 staining patterns, inspired by a recently proposed method for aggregating local image (SIFT) features into a compact and fixed length representation. More specifically we present a novel framework in which aggregated features are mapped into feature vectors in the dissimilarity space where the dimensionality of the descriptors is “naturally reduced”. The final descriptor is low dimensional, while evaluation on a recently published dataset yields state of the art results.

In this work we present a new approach to the extraction of features robust to focal mismatches, for the classification of biological particles characterized by 3 dimensional structures. We use SIFT descriptors in order to encode local gradient, fused with features derived from an introduced adaptive filterbank of Gabor filters. We have evaluated the proposed technique using a dataset consisting of 174 images of pollen grains from 29 species, acquired with a low-cost optical microscope in arbitrary focal planes. The proposed descriptor efficiently captures discriminative information by encoding the local inner and outer structure of the transparent pollens in a focus-tolerant manner, achieving approximately 74.5% classification accuracy, demonstrating that local scale invariant features can be robust even under challenging conditions.

Autoimmune diseases are proven to be connected with the occurrence of autoantibodies in patient serum. Antinuclear autoantibodies (ANAs) identification can be accomplished in a laboratory using indirect immunofluorescence (IIF) imaging. ANAs are characterized by specific “visual” patterns on a humane epithelial cell line (HEp-2). The identification stage is usually done by trained and highly qualified physicians through visual inspection of slides using a fluorescence microscope. The presence of subjectivity in the identification process, the interobserver variability, the increasing demand of highly specialized personnel, suggest that a realization of an automatic classification system is of great significance for the field of autoimmune diseases diagnosis. Moreover CAD systems can be used in a collaborative scheme in order to augment the physicians' capabilities. In this paper a system for automatic classification of staining patterns on single-cell fluorescence images is proposed. Our method utilizes morphological features extracted from a set of binary images derived via multi-level thresholding of fluorescence images. Furthermore, a modified version of Uniform Local Binary Patterns descriptor is incorporated in order to capture local textural information. The classification is performed using a non-linear SVM Classifier. The proposed method is evaluated using a publicly available dataset, recently released for the purposes of HEP-2 Cells classification competition at ICPR 2012, achieving up to 95.9% overall classification accuracy.

In this paper the face recognition problem is addressed in a part-based sparse approach through the comparison of respective facial regions between different images. To this purpose, a sparse coding procedure is applied to non-overlapping patches derived from frontal-face images, in order to extract local facial information. An adequate measure is introduced, incorporating the resulted sparse representation along with the Hamming distance, in order to express pairwise similarities between faces. Finally, a simple Nearest Neighbor classifier is employed to determine the identity of each facial image. In addition, a new criterion is presented for the rejection of outliers. The emerged face recognition scheme is evaluated using publicly available facial image databases, and the results are compared with those of other well-established recognition methods.