A project by Levina reports that a convolutional neural network (CNN) classified static American Sign Language (ASL) letter images from Sign Language MNIST with 97.80% accuracy and 97.80% macro F1 on a held-out test set of 7,172 images. Those figures describe this dataset and evaluation pipeline—not a system that translates full ASL or has demonstrated reliable performance with new signers and camera conditions.
What the project recognizes
The task is image classification: given a still image of a hand shape, predict its letter class. The project uses Sign Language MNIST, described as 28 × 28-pixel grayscale images covering 24 ASL letter classes. J and Z are omitted because their signs involve movement, which a single static image does not represent. The dataset is described as having 27,455 training images and a separate 7,172-image test set.
As an Amazon Associate I earn from qualifying purchases.
This scope matters. Recognizing isolated static letters is not the same as understanding ASL communication, which includes movement and meaning conveyed in context. The reported system should therefore be understood as a letter-image classifier, not an ASL translation tool.
How the models were compared
The project compares four classifier families, but they do not all receive the same input representation. The CNN uses each original 28 × 28 image. Logistic Regression, Random Forest, and Histogram Gradient Boosting instead receive 49 features: averages of the image’s 4 × 4 pixel blocks. Pixel values are scaled to the 0-to-1 range by dividing by 255.
#1 Best Overall
- The only book with comprehensive instruction and online graded video practice quizzes, plus a comprehensive final video exam
- Enhance your signing learning with Barron’s 500 Flash Cards of American Sign Language feature full-color photos with brief descriptions to help you learn practical signs for everyday usage
- Customize your review using the enclosed sorting ring to arrange the cards in an order that best suits your study needs
- Learn from Barron’s--all content is written and reviewed by experts
| Model | Input | Role in comparison |
|---|---|---|
| Logistic Regression | 49 block-averaged features | Baseline classifier |
| Random Forest | 49 block-averaged features | Bagging ensemble |
| Histogram Gradient Boosting | 49 block-averaged features | Boosting ensemble |
| CNN | Original 28 × 28 images | Image-based neural classifier |
Because the CNN sees the full image while the other models see a reduced feature vector, the comparison reflects both classifier choice and input representation. It does not isolate the effect of classifier family while holding the input constant.
Training and evaluation split
The original training portion was split into 23,336 images for training and 4,119 for validation; the 7,172-image test set was kept separate for final evaluation. The project also used three-fold stratified cross-validation on the 23,336 training images, creating a new CNN for each fold. Random Forest hyperparameters were tuned across tree count, maximum depth, and minimum samples per leaf.
Rank #2
- ASL Sign Language Flash Cards for Kids Ages 4+: Teach or reinforce American sign language skills to preschoolers, kindergarteners, and beyond with Carson Dellosa’s American Sign Language Flash Cards!
- Essential Communication Skills: ASL flash cards are a great way for preschool and kindergarten students to learn basic signing communication skills through fun educational games. Each flash card features rounded corners for easy sorting and flipping.
- What’s Included: The asl flash cards set includes 105 total cards, including a resource card and double-sided sign language flash cards covering 122 signs, including numbers 1-20, alphabet letters, sight words, people, animals, and more.
- Working Together: Each toddler flash card features a colorful signing illustration on one side and the correlating word on the other so you can practice alongside your child. The resource card shows a list of all the signs and words in the set.
- Why Carson Dellosa: For more than 40 years, Carson Dellosa has provided solutions for parents and teachers to help their children get ahead and exceed learning goals. Carson Dellosa supports your child’s educational journey every step of the way.
What the reported scores mean
The project reports 97.80% accuracy and 97.80% macro F1 for the CNN on the held-out test set. Accuracy is the share of test images classified correctly. Macro F1 calculates an F1 score for each class and averages those scores, giving each class equal weight rather than letting the most frequent classes dominate.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
The reported 98.70% macro F1 belongs to the tuned Random Forest on the validation set. It is not a test-set result, so it should not be compared as if it were a higher final score than the CNN’s 97.80% test result. The author reports the CNN as the strongest model during cross-validation and validation; among the ensemble methods, Random Forest outperformed Histogram Gradient Boosting, and both outperformed Logistic Regression.
Rank #3
- Develop Language Communication: Promote speech and language development through the use of simple and clear, illustrated flashcards.
- Reduce Anxiety and Build Confidence: Build confidence and understanding by using Amagenius flashcards to expand language and communication skills, encourage response and recognition with the pictorial cues.
- Simple and Effective: Simple diagrams teach ASL effectively and are double sided so that one side is a close up while the other shows the word and picture to give context.
- Portable and Safe: Resistant Linen Finish Cards made from the same material as professional playing cards, these lightweight 8.9 x 5.8 cm round corner cards come in a small box and have and a helpful bungee clip to keep them safe and organised.
- 27 Cards Asl Communication Theme: 27 hand-drawn flashcards illustrating key ideas and items. Ideal for use with learning American sign language and other SEN needs such as Autism, Speech Delay and Selective Mutism. Can also be effective with young children, language learning and neurological diseases such as Alzheimer’s.
These are results reported for this project’s particular split and pipeline. They are not an independent reproduction, and they do not establish what a deployed system would achieve.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Where the CNN made more mistakes
The CNN’s classification report showed lower recall for three classes: about 0.88 for T, 0.91 for S, and 0.92 for I. Recall measures how many examples of a given class the model correctly identifies. The project describes a confusion matrix, but the available reported details do not support listing further class-by-class error counts.
Rank #4
- Comprehensive ASL Learning Tool – The ASL Starter Bundle comes with 240 ASL flash cards with 5 color-coded themed packs and 5 rings for easy sorting. It covers words ranging from basic sight words like "milk" and "A-Z" to words like "winter" and "love," etc.—with 240 practical words including ABCs, Numbers, Colors, Food, Fruits, Emotions, Seasons, and Greetings.
- Larger-Sized ASL Flashcards - Perfect size (5.71" x 3.94") for kids' hands and classroom use, made with thick 350gsm laminated cardstock that is easy to write and wipe off, tear-resistant, and long-lasting. Includes 5 metal binder rings to create custom sign language flashcard sets, plus a sturdy storage box that keeps the ASL cards organized and protected.
- Easy-to-Follow Visual Guides - The ASL flash cards feature vivid visual guides paired with clear written descriptions, making each sign easy to understand and follow. Every card specifies the handshape, location, and movement, so learners can accurately reproduce each sign with confidence. This combination of visual and written instruction supports both visual and reading-based learners, helping beginners build correct signing habits from the very start.
- Perfect for Homeschool or Classroom - The ASL flash cards help to build vocabulary for all ages and skill levels—from toddlers and homeschoolers to advanced ASL students. Teaches nouns, verbs, sight words for real-world use. A must-have for teachers enhancing classroom resources or parents supporting their child's language development.
- Ideal Language Teaching Aids - The sign language flashcard set for beginners is perfect for teachers, parents, and therapists in special education,speech therapy, classrooms, or home learning. Encourages interactive play with memory games, quizzes, and group activities while supporting inclusive communication between deaf and hearing communities.
What the evaluation does not establish
The evaluation uses one image dataset. It does not demonstrate how well the classifier works with different signers, lighting, backgrounds, or camera angles. Nor does it test full sign-language communication: the dataset represents static letters and excludes the movement-dependent letters J and Z.
Quick wins for a faster PC:
Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Clear out junk files and repair common Windows errorsFree Scan →Scan for outdated or missing drivers - takes under a minuteDriver Scan →Consequently, a high score on this held-out test set is evidence of performance on the project’s dataset and split—not proof of signer-independent accuracy or robustness in real-world use. The distinction is especially important when considering a camera-based application, where image conditions and the people producing signs may differ from the dataset.
Quick Recap
How to read the comparison
- For the project’s final reported test result, use the CNN’s 97.80% accuracy and 97.80% macro F1 on 7,172 test images.
- Treat the Random Forest’s 98.70% macro F1 as a validation result, not a test score.
- Remember that the CNN received original images while the other classifiers received 49 block averages, so this is not a controlled comparison of classifier families on identical inputs.
- Interpret all scores within the 24-class static-letter task; they do not measure full ASL translation or performance across new users and conditions.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
