The superharmonic imaging of tissue has the potential for high spatial and contrast resolutions, compared to the fundamental and second harmonic imaging. For this technique, the spectral bandwidth of an ultrasound transducer is divided for transmission of ultrasound and reception of its superharmonics (i.e., higher than the second harmonic). Due to the spectral division for the transmission and reception, transmitted ultrasound energy is not sufficient to induce superharmonics in media without using contrast agents, and it is difficult that a transducer has a -6-dB fractional bandwidth of higher than 100%. For the superharmonic imaging of tissue, thus, multi-frequency array transducers are the best choice if available; transmit and receive elements are separate and have different center frequencies. However, the construction of a multi-frequency transducer for intravascular ultrasound (IVUS) imaging is particularly demanding because of its small size of less than 1 mm. Here, we report a recently developed dual-element focused IVUS transducer for the third harmonic imaging of tissue, which consists of a 35-MHz element for ultrasound transmission and a 105-MHz element for third harmonic reception. For high quality third harmonic imaging, both elements were fabricated to have the same focus at 2.5 mm. The results of tissue mimicking phantom tests demonstrated that the third harmonic images produced by the developed transducer had higher spatial resolution and deeper imaging depth than the fundamental images.

Recent state-of-the-art scene text recognition methods have primarily focused on horizontal text in images. However, in several Asian countries, including China, large amounts of text in signs, books, and TV commercials are vertically directed. Because the horizontal and vertical texts exhibit different characteristics, developing an algorithm that can simultaneously recognize both types of text in real environments is necessary. To address this problem, we adopted the direction encoding mask (DEM) and selective attention network (SAN) methods based on supervised learning. DEM contains directional information to compensate in cases that lack text direction; therefore, our network is trained using this information to handle the vertical text. The SAN method is designed to work individually for both types of text. To train the network to recognize both types of text and to evaluate the effectiveness of the designed model, we prepared a new synthetic vertical text dataset and collected an actual vertical text dataset (VTD142) from the Web. Using these datasets, we proved that our proposed model can accurately recognize both vertical and horizontal text and can achieve state-of-the-art results in experiments using benchmark datasets, including the street view test (SVT), IIIT-5k, and ICDAR. Although our model is relatively simple as compared to its predecessors, it maintains the accuracy and is trained in an end-to-end manner.

Image classification in Remote Sensing and Geographic Information Systems (GIS) containing various land-cover classes is essential for efficient and sustainable land-use estimation, and other tasks like object detection, localization and segmentation. Deep Learning (DL) techniques have shown a tremendous potential in the GIS domain. While Convolutional Neural Networks (CNN) have dominated most of the image analysis domain, a new architecture called transformers have proved to be a unifying solution for several AI-based processing pipelines. Vision Transformers (ViT), a variant of transformers can have comparable and in some cases better accuracy than a CNN. However, they suffer from a significant drawback associated with an excessive use of training parameters. In this research we explore several modifications in the vision transformer architectures, especially MobileViT that can be optimized while boosting accuracy. To verify our proposed approach these new architectures are trained on four land-cover datasets AID, EuroSAT, UC-Merced, and WHU-RS19. Experiments reveal that combination of lightweight convolutional layers including ShuffleNet along with depthwise separable convolutions and average pooling can reduce the trainable parameters by 17.85% and yet achieve higher accuracy than the base MobileViT. It is also observed that utilizing a combination of convolution layers along with multi-headed self attention layers in MobileViT variants provide better performance in capturing local and global features unlike the standalone ViT architecture that utilizes almost 95% more parameters than the proposed MobileViT variant.