close-circle
Close
0%
0%

VizLens: A Screen Reader for the Real World

VizLens uses crowdsourcing and computer vision to robustly and interactively help blind people use inaccessible interfaces in the real world

Similar projects worth following
close
The world is full of physical interfaces that are inaccessible to blind people, from microwaves and information kiosks to thermostats and checkout terminals. We introduce VizLens - an accessible mobile application and supporting backend that can robustly and interactively help blind people use nearly any interface they encounter. VizLens users capture a photo of an inaccessible interface and send it to multiple crowd workers, who work in parallel to quickly label and describe elements of the interface to make subsequent computer vision easier. The VizLens application helps users recapture the interface in the field of the camera, and uses computer vision to interactively describe the part of the interface beneath their finger (updating 8 times per second). We then explore extensions of VizLens that allow it to (i) adapt to state changes in dynamic interfaces, (ii) combine crowd labeling with OCR technology to handle dynamic displays, and (iii) benefit from head-mounted cameras.

The world is full of inaccessible physical interfaces. Microwaves, toasters and coffee machines help us prepare food; printers, fax machines, and copiers help us work; and checkout terminals, public kiosks, and remote controls help us live our lives. Despite their importance, few are self-voicing or have tactile labels. As a result, blind people cannot easily use them. Generally, blind people rely on sighted assistance either to use the interface or to label it with tactile markings. Tactile markings often cannot be added to interfaces on public devices, such as those in an office kitchenette or checkout kiosk at the grocery store, and static labels cannot make dynamic interfaces accessible. Sighted assistance may not always be available, and relying on co-located sighted assistance reduces independence.

Making physical interfaces accessible has been a long-standing challenge in accessibility. Solutions have generally either involved (i) producing self-voicing devices, (ii) modifying the interfaces (e.g., adding tactile markers), or (iii) developing interface- or task-specific computer vision solutions. Creating new devices that are accessible can work, but is unlikely to make it into all devices produced due to cost. The Internet of Things may help solve this problem eventually; as more and more devices are connected and can be controlled remotely, the problem becomes one of digital accessibility, which is easier to solve despite challenges. For example, users may bring their own smartphone with an interface that is accessible to them, and use it to connect to the device. Computer vision approaches have been explored, but are usually brittle and specific to interfaces and tasks. Given these significant challenges, we expect these solutions will neither make the bulk of new physical interfaces accessible going forward nor address the significant legacy problem in even the medium term.

This paper introduces VizLens, a robust interactive screen reader for real-world interfaces. Just as digital screen readers were first implemented by interpreting the visual information the computer asks to display, VizLens works by interpreting the visual information of existing physical interfaces. To work robustly, it combines on-demand crowdsourcing and real-time computer vision. When a blind person encounters an inaccessible interface for the first time, he uses a smartphone to capture a picture of the device and then send it to the crowd. This picture then becomes a reference image. Within a few minutes, crowd workers mark the layout of the interface, annotate its elements (e.g., buttons or other controls), and describes each element. Later, when the person wants to use the interface, he opens the VizLens application, points it toward the interface, and hovers a finger over it. Computer vision matches the crowd-labeled reference image to the image captured in real-time. Once it does, it can detect what element the user is pointing at and provide audio feedback or guidance. With such instantaneous feedback, VizLens allows blind users to interactively explore and use inaccessible interfaces.

In a user study, 10 participants effectively accessed otherwise inaccessible interfaces on several appliances. Based on their feedback, we added functionality to adapt to interfaces that change state (common with touchscreen interfaces), read dynamic information with crowd-assisted Optical Character Recognition (OCR), and experimented with wearable cameras as an alternative to the mobile phone camera. The common theme within VizLens is to trade off between the advantages of humans and computer vision to create a system that is nearly as robust as a person in interpreting the user interface and nearly as quick and low-cost as a computer vision system. The end result allows a long-standing accessibility problem to be solved in a way that is feasible to deploy today.

uist16-VizLens.pdf

Paper about details of the VizLens project.

Adobe Portable Document Format - 5.42 MB - 09/29/2016 at 04:28

eye
Preview
download-circle
Download

  • VizLens::Wearable Cameras

    Anhong Guo09/29/2016 at 04:45 0 comments

    56.7% of the images took by the blind participants for crowd evaluation failed the quality qualifications, which suggests there is a strong need to assist blind people in taking photos. In our user evaluation, several participants also expressed their frustration with aiming and especially keeping good framing of the camera. Wearable cameras such as the Google Glass have the advantage of leaving the user's hand free, easier to keep image framing stable, and naturally indicating the field of interest. We have ported the VizLens mobile app to Google Glass platform, and pilot tested with several participants. Our initial results show that participants were generally able to take better framed photos with the head-mounted camera, suggesting that wearable cameras may address some of the aiming challenges.

  • VizLens::LCD Display Reader

    Anhong Guo09/29/2016 at 04:45 0 comments

    VizLens v2 also supports access to LCD displays via OCR. We first configured our crowd labeling interface and asked crowd workers to crop and identify dynamic and static regions separately. This both improves computational efficiency and reduces the possibility of interference from background noises, making it faster and more accurate for later processing and recognition. After acquiring the cropped LCD panel from the input image, we applied several image processing techniques, including first image sharpening using unsharp masking for enhanced image quality and intensity-based thresholding to filter out the bright text. We then performed morphological filtering to join the separate segments of 7-segment displays (which are commonly used in physical interfaces) to form contiguous characters, which is necessary since OCR assumes individual segments correspond to individual characters. For the dilation's kernel, we used height > 2 x width to prevent adjacent characters from merging while forming single characters. Next, we applied small blob elimination to filter out noise, and selective color invertion to create black text on a white background, which OCR performs better on. Then, we performed OCR on the output image using the Tesseract Open Source OCR Engine. When OCR fails to get an output, our system dynamically adjusts the threshold for intensity thresholding for several iterations.

  • VizLens::State Detection

    Anhong Guo09/29/2016 at 04:43 0 comments

    Many interfaces include dynamic components that cannot be handled by the original version of VizLens, such as an LCD screen on a microwave, or the dynamic interface on self-service checkout counter. As an initial attempt to solve this problem, we implemented a state detection algorithm to detect system state based on previously labeled screens. For the example of a dynamic coffeemaker, sighted volunteers first go through each screen of the interface and take photos. Crowd workers will label each interface separately. Then when the blind user accesses the interface, instead of only performing object localization for one reference image, our system will first need to find the matching reference image given the current input state. This is achieved by computing SURF keypoints and descriptors for each interface state reference image, performing matches and finding homographies between the video image with all reference images, and selecting the one with the most inliers as the current state. After that, the system can start providing feedback and guidance for visual elements for that specific screen. As a demo in our video, we show VizLens helping a user navigate the six screens of a coffeemaker with a dynamic screen.

  • VizLens V2

    Anhong Guo09/29/2016 at 04:43 0 comments

    Based on participant feedback in our user evaluation, we developed VizLens v2. Specifically, we focus on providing better feedback and learning of the interfaces.

    For VizLens to work properly it is important to inform and help the users aim the camera centrally at the interface. Without this feature, we found the users could `get lost' - they were unaware that the interface was out of view and still kept trying to use the system. Our improved design helps users better aim the camera in these situations: once the interface is found, VizLens automatically detects whether the center of the interface is inside the camera frame; and if not, it provides feedback such as ``Move phone to up right" to help the user adjust the camera angle.

    To help users familiarize themselves with an interface, we implemented a simulated version with visual elements laid out on the touchscreen for the user to explore and make selection. The normalized dimensions of the interface image as well as each element's dimensions, location and label make it possible to simulate buttons on the screen that react to users' touch, thus helping them get a spatial sense of where these elements are located.

    We also made minor function and accessibility improvements such as vibrating the phone when the finger reaches the target in guidance mode, making the earcons more distinctive, supporting standard gestures for back, and using the volume buttons for taking photos when adding a new interface.

  • System Implementation

    Anhong Guo09/29/2016 at 04:41 0 comments

    VizLens consists of three components: (i) mobile application, (ii) web server, and (iii) computer vision server.

    Mobile App

    The iOS VizLens app allows users to add new interfaces (take a picture of the interface and name it), select a previously added interface to get interactive feedback, and select an element on a previously added interface to be guided to its location. The VizLens app was designed to work well with the VoiceOver screen reader on iOS.

    Web Server

    The PHP and Python web server handles image uploads, assigns tasks to Amazon Mechanical Turk workers for segmenting and labeling, hosts the worker interface, manages results in a database and responds to requests from the mobile app. The worker interfaces are implemented using HTML, CSS, and Javascript.

    Computer Vision Server

    The computer vision pipeline is implemented using C++ and the OpenCV Library. The computer vision server connects to the database to fetch the latest image, process it, and write results back to the database. Running real-time computer vision is computationally expensive. To reduce delay, VizLens uses OpenCV with CUDA running on GPU for object localization. Both the computer vision server and the web server are hosted on an Amazon Web Services EC2 g2.2xlarge instance, with a high-performance NVIDIA GRID K520 GPU, including 1,536 CUDA cores and 4GB of video memory.

    Overall Performance

    Making VizLens interactive requires processing images at interactive speed. In the initial setup, VizLens image processing was run on a laptop with 3GHz i7 CPU, which could process 1280x720 resolution video at only 0.5 fps. Receiving feedback only once every 2 seconds was too slow, thus we moved processing to a remote AWS EC2 GPU instance, which achieves 10 fps for image processing. Even with network latency (on wifi) and the phone's image acquisition and uploading speed, VizLens still runs at approximately 8fps with 200ms latency.

  • Formative Study

    Anhong Guo09/29/2016 at 04:38 0 comments

    We conducted several formative studies to better understand how blind people currently access and accommodate inaccessible interfaces. We first went to the home of a blind person, and observed how she cooked a meal and used home appliances. We also conducted semi-structured interviews with six blind people (aged 34-73) about their appliances use and strategies for using inaccessible appliances. Using a Wizard-of-Oz approach, we asked participants to hold a phone with one hand and move their finger around a microwave control panel. We observed via video chat and read aloud what button was underneath their finger.

    We extracted the following key insights, which we used in the design of VizLens:

    • Participants felt that interfaces were becoming even less accessible, especially as touchpads replace physical buttons. However, participants did not generally have problems locating the control area of the appliances, but have problems with finding the specific buttons contained within it.
    • Participants often resorted to asking for help, such as a friend or stranger: frequently seeking help created a perceived social burden. Furthermore, participants worried that someone may not be available when they are most needed. Thus, it is important to find alternate solutions that can increase the independence of the visually impaired people in their daily lives.
    • Labeling interfaces with Braille seems a straightforward solution but means only environments that have been augmented are accessible. Furthermore, fewer than 10 percent blind people in the United States read Braille.
    • Participants found it difficult to aim the phone's camera at the control panel correctly. In an actual system, such difficulty might result in loss of tracking, thus interrupting the tasks and potentially causing confusion and frustration.
    • Providing feedback with the right details, at the right time and frequency is crucial. For example, participants found it confusing when there was no feedback when their finger was outside of the control panel, or not pointing at a particular button. However, inserting feedback in these situations brings up several design challenges, e.g., the granularity and frequency of feedback.

View all 6 project logs

Enjoy this project?

Share

Discussions

Similar Projects

Does this project spark your interest?

Become a member to follow this project and never miss any updates