Microvasculature analysis is an important task in the medical field due to its various applications. It has been used for the diagnosis and threat of diseases in fields such as ophthalmology, dermatology, and neurology by measuring relative blood flow or blood vessel morphological properties. However, light scattering at the periphery of the blood vessel causes a decrease in contrast around the vessel borders and an increase in the noise of the image, making the localization of blood vessels a challenging task. Therefore, this work proposes integrating known information from the experimental setup into a deep learning architecture with multiple inputs to improve the generalization of a computational model for the segmentation of blood vessels and depth estimation in a single inference step. The proposed R-UNET + ET + LA obtained an intersection over union of 0.944 ± 0.065 and 0.812 ± 0.080 in the classification task for validation (in vitro) and test sets (in vivo), respectively, and a root mean squared error of 0.0085 ± 0.0275 $\mathsf{\mu }$m in the depth estimation. This approach improves the generalization of current solutions by pre-training with in vitro data and adding information from the experimental setup. Additionally, the method can infer the depth of a blood vessel pixel by pixel instead of in regions as the current state of the art does.

Facial expression recognition is related to the automatic identification of affective states of a subject by computational means. Facial expression recognition is used for many applications, such as security, human-computer interaction, driver safety, and health care. Although many works aim to tackle the problem of facial expression recognition, and the discriminative power may be acceptable, current solutions have limited explicative power, which is insufficient for certain applications, such as facial rehabilitation. Our aim is to alleviate the current limited explicative power by exploiting explainable fuzzy models over sequences of frontal face images. The proposed model uses appearance features to describe facial expressions in terms of facial movements, giving a detailed explanation of what movements are in the face, and why the model is making a decision. The model architecture was selected to keep the semantic meaning of the found facial movements. The proposed model can discriminate between the seven basic facial expressions, obtaining an average accuracy of 90.8±14%, with a maximum value of 92.9±28%.

Blood vessel diameter estimation is helpfully in areas such as medicine, dermatology, neuroscience or ophthalmology. Blood vessel estimation plays an important role in diagnosis of cardiovascular diseases, also its useful to validate blood flow dynamics of a blood vessel. This paper addresses a method based on region growing for blood vessel diameter and orientation estimation. The proposed methodology first pre-process a laser speckle contrast image to obtain a certain amount of seeds that grew among the blood vessels located. All the regions contribute information about the blood vessels and they serve to build a map representing the size of the located blood vessels.

Microvasculature analysis in biomedical images is essential in the medical area to evaluate diseases by extracting properties of blood vessels, such as relative blood flow or morphological measurements such as diameter. Given the advantages of Laser Speckle Contrast Imaging (LSCI), several studies have aimed to reduce inherent noise to distinguish between tissue and blood vessels at higher depths. These studies have shown that computing Contrast Images (CIs) with Analysis Windows (AWs) larger than standard sizes obtains better statistical estimators. The main issue is that larger samples combine pixels of microvasculature with tissue regions, reducing the spatial resolution of the CI. This work proposes using adaptive AWs of variable size and shape to calculate the features required to train a segmentation model that discriminates between blood vessels and tissue in LSCI. The obtained results show that it is possible to improve segmentation rates of blood vessels up to 45% in high depths (≈900 $\mathsf{\mu }\mathrm{m}$) by extracting features adaptively. The main contribution of this work is the experimentation with LSCI images under different depths and exposure times through adaptive processing methods, furthering the understanding the performance of the different approaches under these conditions. Results also suggest that it is possible to train a segmentation model to discriminate between pixels belonging to blood vessels and those belonging to tissue. Therefore, an adaptive feature extraction method may improve the quality of the features and thus increase the classification rates of blood vessels in LSCI.

Berry production is increasing worldwide each year; however, high production leads to labor shortages and an increase in wasted fruit during harvest seasons. This problem opened new research opportunities in computer vision as one main challenge to address is the uncontrolled light conditions in greenhouses and open fields. The high light variations between zones can lead to underexposure of the regions of interest, making it difficult to classify between vegetation, ripe, and unripe blackberries due to their black color. Therefore, the aim of this work is to automate the process of classifying the ripeness stages of blackberries in normal and low-light conditions by exploring the use of image fusion methods to improve the quality of the input image before the inference process. The proposed algorithm adds information from three sources: visible, an improved version of the visible, and a sensor that captures images in the near-infrared spectra, obtaining a mean F1 score of $0.909\pm 0.074$ and $0.962\pm 0.028$ in underexposed images, without and with model fine-tuning, respectively, which in some cases is an increase of up to 12% in the classification rates. Furthermore, the analysis of the fusion metrics showed that the method could be used in outdoor images to enhance their quality; the weighted fusion helps to improve only underexposed vegetation, improving the contrast of objects in the image without significant changes in saturation and colorfulness.

Advanced Driver Assistance Systems (ADAS) aim to automate transportation fully. A key part of this automation includes tasks such as traffic light detection and automatic braking. While indoor experiments are prevalent due to computational demands and safety concerns, there is a pressing need for research and development of new features to achieve complete automation, addressing real-world implementation challenges by testing them in outdoor environments. These systems seek to provide precise synchronization for decision-making processes and explore algorithms beyond emergency responses, enabling braking actions with short reaction times. Therefore, this work proposes a level 1 ADAS for automatic braking. The implementation uses an NVIDIA Jetson TX2 and a ZED stereo camera for traffic light detection, which, in addition to the depth map provided by the camera and a fuzzy inference system, make the decision to perform automatic braking based on the distance and current state of the traffic light. The contributions of this research work are the development and validation of a one-stage traffic light state detector using EfficientDet D0, a brake profile using fuzzy logic, and the validation with an on-road experiment in Mexico. The traffic light detection model obtained a mAP of 0.96 for distances less than 13 m and 0.89 for 15 m, with an average RMSE of 0.9 m and 0.05 m in the braking force applied, respectively. Integrated systems have a response time of 0.23 s, taking a step further in the state-of-the-art.