Urdu Handwriting Practice App for Children with Stroke Order and Letter Form Feedback
Build a tablet and phone app where young children trace and write Urdu letters with a finger or stylus, and the app checks stroke order, direction, dot placement and the joined forms letters take at the start, middle and end of words, then shows exactly what to fix. Teachers in crowded classrooms cannot watch every child form every letter, and bad habits set early. The technical core is recognising and comparing handwriting as a sequence of strokes, not as a finished image.
Intermediate
A small team, or one strong student willing to learn something new.1 semester · 2 to 3 students
7 to ship
4 optional extrasSuggested stack
What you should ship
- A drawing canvas that records each stroke as timed points, with tracing guides that fade as the child improves
- Reference stroke templates for all Urdu letters and their joined forms, recorded with a teacher
- A checker for stroke count, order, direction, shape and dot position, with per-mistake feedback
- Animated demonstrations of the correct way to write each letter
- Practice sets that move from isolated letters to joined forms to short words
- Progress records per child and a simple teacher view for a class on a shared tablet
- A collected and consented set of children's strokes, and an evaluation against teacher judgement
If you have time left
- A sequence model that recognises which letter or word was written, for free writing practice
- Audio feedback in Urdu for children who cannot yet read instructions
- Sindhi or Pashto letter sets
- Detecting signs of motor difficulties to suggest a teacher takes a closer look
The problem: letters learned the wrong way
Urdu script is hard for young children. Letters change shape depending on whether they come at the start, middle or end of a word. Dots above and below decide which letter it is. Writing runs right to left, and the order and direction of strokes affect how well letters join later. A child who learns to draw a letter backwards, or adds dots in the wrong place, can carry the habit for years.
In a class of forty, a teacher sees the finished page, not how each letter was formed. By the time a mistake is noticed, it is practised.
What already exists and the gap
- Taleemabad offers Pakistani children animated lessons and games across subjects, including Urdu.
- Read Along by Google helps children practise reading aloud in several languages, including Urdu.
- Generic tracing apps let children trace letters, usually checking only whether the finger stayed near the line.
As far as their public descriptions go, these focus on video lessons, games and reading rather than checking how each Urdu letter was written stroke by stroke. The gap is a writing practice app that watches how a letter is formed, order, direction, dots and joined forms, and tells the child exactly what to change.
Inspiration
"Fast multi-language LSTM-based online handwriting recognition" by Victor Carbune and colleagues at Google, published in the International Journal on Document Analysis and Recognition in 2020, describes the system behind handwriting input for 102 languages. It treats handwriting as a sequence of pen movements rather than an image, and encodes strokes efficiently with Bézier curves. Your project uses the same online view of handwriting, but instead of only recognising letters, it compares a child's strokes to a correct reference and explains the difference. The recognition idea becomes useful later, in the stretch goal for free writing practice, once the template checks work well.
What you build
- Children trace and then write letters, see a gentle animation of what went wrong and try again.
- Teachers see which letters each child struggles with, on a shared class tablet.
- Parents can use the same app at home with one child's profile.
The app must be usable by a five-year-old: big targets, no reading needed to navigate, short sessions and lots of encouragement. Feedback should point to one thing at a time, such as "start from the right" or "the dot goes below", rather than a score.
The technically interesting part
- Online handwriting. Each stroke is a sequence of points with timing. Comparing a child's stroke to a template means aligning sequences of different lengths and speeds; dynamic time warping is a strong, explainable starting point.
- Explaining mistakes. It is not enough to say "wrong". Separate checks for stroke count, order, direction and shape, and a separate check for dot count and position relative to the letter body, let you give one specific piece of feedback.
- Tolerance. Children's strokes are wobbly. Too strict and every attempt fails; too lenient and errors pass. Tune tolerance with a teacher's judgement on real attempts.
- Joined forms. Medial and final forms connect to neighbours. Start with isolated letters, then add joined forms as separate templates.
How to evaluate it
- Agreement with a teacher: on a set of recorded attempts, compare the app's accept or reject decisions and its stated mistake with the teacher's.
- Feedback accuracy: share of rejected attempts where the stated mistake was the real one.
- Learning trial: over two or three weeks with a small group, with consent, compare stroke order errors at the start and the end.
- Performance: feedback delay on a low-cost tablet, which should feel instant to a child.
- Engagement: how many practice attempts children make per session, and whether they return without being asked.
Suggested plan
- Weeks 1 to 3: read the paper, record reference strokes with a teacher, design the canvas.
- Weeks 4 to 7: stroke recording, alignment and the individual checks.
- Weeks 8 to 10: feedback animations, practice sets and progress records.
- Weeks 11 to 13: school trial with consent, tuning tolerance with the teacher.
- Weeks 14 to 15: evaluation, report and demo.
Path to a product
Schools, low-cost private school chains and education programmes need tools that help with early literacy at scale. A free app for parents with a paid classroom version, or a licence to an existing education platform, is realistic. The project shows careful interaction design and applied sequence modelling, both valuable in education technology.
Scope warning
Do not try to recognise free handwriting in the main scope; checking known letters against templates is enough. Do not collect names, photos or audio of children; use class roll numbers. Get consent from the school and parents before recording any child's strokes.
Learn what you need on Sefism
- Mobile development roadmap: building touch interfaces and offline storage.
- UI/UX design roadmap: designing for young children and testing with them.
- Flutter Documentation: custom painting and gesture handling.
- Machine learning roadmap: sequence comparison and evaluation.
- Kotlin Documentation: if you build natively for Android.
Get help with this idea
The risk is feedback that is too strict or too vague for young children. Tauseef can help you plan the teacher partnership, tune the checks and design a fair classroom trial. If you are new here, create a free account first.
Ideas and guidance, not finished projects
These are project ideas and scoping guidance, published free for students to use as a starting point. I do not build, write, or sell final-year projects, and I do not complete coursework for anyone. Take an idea, make it yours, and build it.
Not sure this one fits you?
I help students pick an idea that matches their skills and their deadline, then scope it down until it is finishable. Guidance only, never done for you.
Stuck on something specific?
Writing only gets you so far. If you want an answer to your situation rather than the general case, book a session and we will work through it together. Sessions are free for approved Sefism members, and a few slots open each week.
Follow along
New writing, resources and project ideas land here first.